API World + CloudX + DataWeek 2025

API World + CloudX + DataWeek 2025

12:00pm PDT

PRO WORKSHOP (DataWeek): Building a RAG System for Video Search and Analysis

Wednesday September 3, 2025 12:00pm - 12:50pm PDT

DataWeek -- Main Stage

Elizabeth Fuentes Leone, AWS, Developer Advocate

This talk addresses the challenge of making video content searchable and analyzable using modern AI techniques. While text and image RAG systems are common, video presents unique challenges due to its multimodal nature combining visual frames and audio content.

Speakers

Elizabeth Fuentes Leone

Developer Advocate, AWS

As a Data Analytics and Machine Learning/Artificial Intelligence (ML/AI) Specialist, my mission is to break down complex concepts into easily understandable terms. I strive to develop innovative solutions that tackle real-world challenges effectively. By sharing my knowledge and experience... Read More →

Wednesday September 3, 2025 12:00pm - 12:50pm PDT
DataWeek -- Main Stage

Additional Topics RAG & LLMs
Talk Type PRO Workshop Day (Wed)
Tracks DataWeek, Data Science and Machine Learning (DataWeek), Data Engineering / Architecture and Streaming (DataWeek)
In-Person/Virtual In Person

3:00pm PDT

PRO WORKSHOP (DataWeek): AI-Driven Data Optimization: Smart Strategies for Scalability and Performance

Wednesday September 3, 2025 3:00pm - 3:50pm PDT

DataWeek -- Main Stage

Indu Chaube, Cisco Systems, Senior Software Engineer

In my session, 'AI-Driven Data Optimization: Smart Strategies for Scalability and Performance,' I will examine the transformative role of artificial intelligence in modern data management. This session will delve into how AI-powered techniques streamline data ingestion, automate preprocessing workflows, enhance storage efficiency, and enable real-time analytics for intelligent decision-making. Through advanced optimization strategies, AI-driven solutions significantly reduce latency, improve resource allocation, and ensure seamless scalability in high-volume data ecosystems. Attendees will gain a deep understanding of AI’s impact on data governance, predictive analytics, and automation, learning how to implement robust end-to-end pipelines that drive operational efficiency and business intelligence.

Speakers

Indu Chaube

Senior Software Engineer, Cisco Systems

Indu Chaube is a highly accomplished software architect and visionary leader with more than a decade-long track record in software product design and development, encompassing User Interface, User Experience, and web API domains. Collaborating with industry giants like Cisco and SAMSUNG... Read More →

Wednesday September 3, 2025 3:00pm - 3:50pm PDT
DataWeek -- Main Stage

Additional Topics RAG & LLMs, Predictive Analytics
Talk Type PRO Workshop Day (Wed)
Tracks DataWeek, Data Tools / Technology and Management (DataWeek)
In-Person/Virtual In Person

4:00pm PDT

PRO WORKSHOP (DataWeek): Leveraging Open Source AI Securely and Privately

Wednesday September 3, 2025 4:00pm - 4:50pm PDT

DataWeek -- Main Stage

JJ Asghar, IBM, Developer Advocate

Honestly, you're probably jealous of those people saying "ChatGPT" is making their lives easier. You may think that leveraging AI is this generation's adoption of the calculator. I'm here to say yes, you are right, but let's be honest: we have no idea how the ChatGPTs of the world are trained or if they are secure.
If you run a technology company, your data is your secret sauce; if your boss found out you were leveraging ChatGPT to do your job, would they be happy? Probably not.
In this presentation, we will explore how LLMs work locally through hands-on activities, such as setting up some local open-source private and free LLMs to help you get closer to the promise of generative AI.
Overall, this presentation will start with some basic installation leveraging Ollama and VS Code or any of the JetBrains platforms (and you'll learn what that means and what the differences are!), then pull in AnythingLLM and/or OpenWebUI to help give you a straightforward chat-like interface to your LLM. We will provide you with the knowledge, tools, some generic prompts, and use cases to gain more confidence in your daily life by leveraging LLMs.
You'll walk out of the workshop with a working LLM that you can engage with no fees or usage, all locally and securely.

Speakers

JJ Asghar

Developer Advocate, IBM

JJ works as a Developer Advocate representing IBM worldwide. He mainly focuses on open-source AI and OpenShift, trying to help companies and users successfully onboard to the Cloud-Native ecosystem. He’s also known in the DevOps tooling ecosystem and generalized Linux communities... Read More →

Wednesday September 3, 2025 4:00pm - 4:50pm PDT
DataWeek -- Main Stage

Additional Topics Generative AI, RAG & LLMs
Talk Type PRO Workshop Day (Wed)
Tracks DataWeek, AI Models and Management (DataWeek), Data Tools / Technology and Management (DataWeek)
In-Person/Virtual In Person

5:00pm PDT

PRO WORKSHOP (DataWeek): From Data to Insights in Minutes: Accelerating Business Growth with AutoML and LLM-Powered Data Prep

Wednesday September 3, 2025 5:00pm - 5:50pm PDT

DataWeek -- Main Stage

Shailaja Sampat, Fujitsu Research of America, Senior Researcher

- Are you tired of manually processing large datasets in spreadsheets? 
- Have you considered using Machine Learning (ML) to automate your tasks but feel limited by your coding skills or time constraints?
 - Looking for ways to reduce the time spent in making your data AI-ready, despite your ML background?

If these challenges sound familiar, this session is for you!

Traditionally, building predictive models has required specialized coding and statistical expertise. Moreover, data professionals often dedicate over 80% of their time to the labor-intensive data-wrangling process- to prepare raw data for consumption by automated machine learning (AutoML) tools. To overcome these hurdles, we introduce AutoDW, an innovative data wrangler that utilizes the power of Large Language Models (LLMs) and sophisticated automation to facilitate the seamless preparation of AI-ready data. This session will demonstrate how the synergistic application of AutoDW and AutoML empowers users to rapidly develop predictive prototypes for their business use cases end-to-end without writing any code. Through step-by-step instruction and a live demonstration, attendees will witness AutoDW's intelligent data processing, observe AutoML's autonomous algorithm selection tailored to specific applications, and, most importantly, gain a comprehensive understanding of how to interpret the resulting predictive outputs.

#AutoML #DataWrangling #NoCodeML #FastMLPrototyping #DataDrivenDevelopment

Speakers

Shailaja Sampat

Senior Researcher, Fujitsu Research of America

Shailaja Sampat is a senior researcher in the AI lab at Fujitsu's research division in the USA. She earned her Ph.D. from Arizona State University, with a thesis focusing on the intersection of natural language processing and computer vision. Her current research spans autoML, data... Read More →

Wednesday September 3, 2025 5:00pm - 5:50pm PDT
DataWeek -- Main Stage

Additional Topics RAG & LLMs
Talk Type PRO Workshop Day (Wed)
Tracks DataWeek, Data Science and Machine Learning (DataWeek), Data Tools / Technology and Management (DataWeek)
In-Person/Virtual In Person

9:30am PDT

PRO Session (DataWeek): Intelligent Automation of Data Engineering Workflows with LLMs

Thursday September 4, 2025 9:30am - 9:55am PDT

DataWeek -- Main Stage

Manohar Sai Jasti, Workday, Analytics Engineer

I will share how I developed an AI-driven system to transform raw SQL into production-ready dbt models using Large Language Models (LLMs). By combining retrieval-augmented generation techniques with dbt’s semantic framework, I automated SQL refactoring, modularization, testing, and documentation. This approach accelerates data engineering workflows, reduces manual effort, and enables scalable, production-ready analytics pipelines. I will walk through the architecture, challenges faced during scaling, validation strategies for AI-generated SQL, and key lessons learned from deploying this solution in real-world environments. Attendees will gain practical insights into applying LLMs for data workflow automation, improving pipeline quality, and driving faster AI productionization across modern data stacks.

Speakers

Manohar Sai Jasti

Analytics Engineer, Workday

Manohar Sai Jasti is an experienced Analytics Engineer specializing in building efficient and scalable data pipelines. With expertise in tools like dbt, Trino, and cloud platforms, he helps organizations turn data into actionable insights. Manohar is passionate about simplifying data... Read More →

Thursday September 4, 2025 9:30am - 9:55am PDT
DataWeek -- Main Stage

Additional Topics RAG & LLMs
Talk Type PRO Session
Tracks DataWeek, Data Engineering / Architecture and Streaming (DataWeek)
In-Person/Virtual In Person

3:30pm PDT

OPEN Session (DataWeek): Balancing Velocity with Academic Rigor When Building with LLMs

Thursday September 4, 2025 3:30pm - 3:55pm PDT

DataWeek -- Main Stage

Lauren Peate, Multitudes, CEO & founder

We’re all building AI features now. But building with LLMs brings its own challenges – namely: How can we use cutting-edge practices, weave in AI ethics, and consider the cost of different models without blowing past delivery dates. Not to mention making sure that the features we build will be stable, reliable and maintainable in the future.

We recently built our first LLM feature, to show the quality of feedback given in code reviews. In 1 month, we did a literature review, consultation with academic experts, data labelling, model experimentation, a cost assessment, and finally, all the ML engineering to launch it into production. The outcome: <1% extreme misclassification and zero hallucinations. In this talk, we’ll share our approach to building LLM features – how we partnered with academia (without being delayed by their timelines), what tooling we used, and how we made the cost and money tradeoffs to keep business stakeholders happy. I’ll also speak to how we built this into our microservices architecture, including how we used tools to generate structured outputs from LLMs on top of AWS’s Bedrock API to have parseable responses from a range of models.

You'll walk away with practical strategies for leading your own teams through AI implementations, identifying ethical issues early, addressing them efficiently, and still delivering on time and on budget.

Speakers

Lauren Peate

CEO & founder, Multitudes

Lauren Peate is the CEO and founder of Multitudes, which helps engineering teams improve delivery sustainably. She’s focused her career on using data to support people, including as the founder of Ally Skills NZ, a consultancy helping global tech companies improve team performance... Read More →

Thursday September 4, 2025 3:30pm - 3:55pm PDT
DataWeek -- Main Stage

Additional Topics Microservices, RAG & LLMs, Privacy and Ethics
Talk Type OPEN Session
Tracks DataWeek, AI Models and Management (DataWeek), Data Science and Machine Learning (DataWeek)
In-Person/Virtual In Person

10:00am PDT

PRO Session (DataWeek): Data Sovereignty in the Age of AI

Friday September 5, 2025 10:00am - 10:25am PDT

DataWeek -- Main Stage

Michel Tricot, Airbyte, Co-founder and CEO

This session will explore the intersection of data sovereignty and artificial intelligence, addressing how organizations can maintain control of their valuable data assets while still leveraging the power of AI. Drawing from extensive experience building open-source data infrastructure solutions, Michel will illuminate the challenges companies face when integrating AI into their data ecosystems without compromising ownership, security, or compliance requirements.

The session targets data leaders, CDOs, and enterprise architects who are navigating the complex landscape of AI adoption while maintaining strict data governance standards. Michel will share practical frameworks for implementing a self-managed data integration strategy that enables AI innovation while preserving first-party data sovereignty—a crucial consideration as regulatory requirements around data protection continue to evolve globally. Attendees will gain actionable insights on building resilient data architectures that support AI initiatives without surrendering control of sensitive information.

This session aligns perfectly with Data Week's focus on "Data Engineering & Governance" and "AI & ML" tracks, offering attendees a unique perspective on balancing innovation with control. Conference participants will benefit from Michel's vision of how open-source data integration infrastructure can serve as the foundation for responsible AI development, empowering organizations to build competitive advantages while maintaining complete sovereignty over their data. The presentation will include real-world examples of companies that have successfully implemented these principles.

Speakers

Michel Tricot

Co-founder and CEO, Airbyte

Michel Tricot is co-founder and CEO of Airbyte, the open data movement platform. The company was started in 2020 with a vision of commoditizing data integration pipelines across all industries and organizations and today has more than 170,000 deployments. Michel has been working in... Read More →

Friday September 5, 2025 10:00am - 10:25am PDT
DataWeek -- Main Stage

Additional Topics Integration Strategy, RAG & LLMs
Talk Type PRO Session
Tracks DataWeek, AI Models and Management (DataWeek), Data Engineering / Architecture and Streaming (DataWeek)
In-Person/Virtual In Person

11:30am PDT

OPEN Session (DataWeek): Rearchitecting Data Processing for Today’s Demands

Friday September 5, 2025 11:30am - 11:55am PDT

DataWeek -- Main Stage

Rajan Goyal, DataPelago, CEO & Co-founder

IT leaders face mounting pressure to leverage their organization’s data for genAI and lakehouse analytics. Yet, with data volumes doubling every two years and nearly 90% of new data being unstructured, traditional data processing architectures can’t keep up. Existing systems were designed for structured data and CPU-based computing, and businesses are finding they struggle with processing latency, high costs, and siloed data. In fact, more than 80% of IT leaders say that data silos are hindering digital transformation.

To drive value in today’s data environment, IT leaders need to implement new data processing architectures that are designed to handle massive volumes of complex data and are capable of taking advantage of the accelerated hardware (GPUs, FPGAs, CPU/SIMD, etc.) available in today’s cloud environments.

In this session, DataPelago CEO Rajan Goyal will outline the shortcomings of current data processing architectures and introduce attendees to the Universal Data Processing Engine, a software solution that sits between a data lake and query engine. Overcoming the shortcomings of traditional processing models, the UDPE is designed to handle all types of data (structured, unstructured, semi-structured) and work on top of any hardware. Integrating seamlessly into any tech stack, it accelerates data processing speed by 2-3x while cutting processing costs by 30-60% — enabling organizations to utilize all of their data for lakehouse analytics and AI workloads.

Speakers

Rajan Goyal

CEO & Co-founder, DataPelago

Rajan is the co-founder and Chief Executive Officer of DataPelago, the company revolutionizing data processing for the accelerated computing era. His expertise and visionary approach have been instrumental in shaping the future of data infrastructure and processing. A seasoned innovator... Read More →

Friday September 5, 2025 11:30am - 11:55am PDT
DataWeek -- Main Stage

Additional Topics RAG & LLMs
Talk Type OPEN Session
Tracks DataWeek, OPEN Session, Data Tools / Technology and Management (DataWeek)
In-Person/Virtual In Person

9:00am PDT

[Virtual] PRO WORKSHOP (DataWeek): Building a RAG System for Video Search and Analysis

Wednesday September 10, 2025 9:00am - 9:50am PDT

VIRTUAL DataWeek -- Main Stage

Elizabeth Fuentes Leone, AWS, Developer Advocate

This talk addresses the challenge of making video content searchable and analyzable using modern AI techniques. While text and image RAG systems are common, video presents unique challenges due to its multimodal nature combining visual frames and audio content.

Speakers

Elizabeth Fuentes Leone

Developer Advocate, AWS

As a Data Analytics and Machine Learning/Artificial Intelligence (ML/AI) Specialist, my mission is to break down complex concepts into easily understandable terms. I strive to develop innovative solutions that tackle real-world challenges effectively. By sharing my knowledge and experience... Read More →

Wednesday September 10, 2025 9:00am - 9:50am PDT
VIRTUAL DataWeek -- Main Stage

Additional Topics RAG & LLMs
Talk Type PRO Workshop Day (Wed)
Tracks DataWeek, Data Science and Machine Learning (DataWeek), Data Engineering / Architecture and Streaming (DataWeek), Virtual
In-Person/Virtual Virtual

12:00pm PDT

[Virtual] PRO WORKSHOP (DataWeek): AI-Driven Data Optimization: Smart Strategies for Scalability and Performance

Wednesday September 10, 2025 12:00pm - 12:50pm PDT

VIRTUAL DataWeek -- Main Stage

Indu Chaube, Cisco Systems, Senior Software Engineer

In my session, 'AI-Driven Data Optimization: Smart Strategies for Scalability and Performance,' I will examine the transformative role of artificial intelligence in modern data management. This session will delve into how AI-powered techniques streamline data ingestion, automate preprocessing workflows, enhance storage efficiency, and enable real-time analytics for intelligent decision-making. Through advanced optimization strategies, AI-driven solutions significantly reduce latency, improve resource allocation, and ensure seamless scalability in high-volume data ecosystems. Attendees will gain a deep understanding of AI’s impact on data governance, predictive analytics, and automation, learning how to implement robust end-to-end pipelines that drive operational efficiency and business intelligence.

Speakers

Indu Chaube

Senior Software Engineer, Cisco Systems

Indu Chaube is a highly accomplished software architect and visionary leader with more than a decade-long track record in software product design and development, encompassing User Interface, User Experience, and web API domains. Collaborating with industry giants like Cisco and SAMSUNG... Read More →

Wednesday September 10, 2025 12:00pm - 12:50pm PDT
VIRTUAL DataWeek -- Main Stage

Additional Topics RAG & LLMs, Predictive Analytics
Talk Type PRO Workshop Day (Wed)
Tracks DataWeek, Data Tools / Technology and Management (DataWeek), Virtual
In-Person/Virtual Virtual

1:00pm PDT

[Virtual] PRO WORKSHOP (DataWeek): Leveraging Open Source AI Securely and Privately

Wednesday September 10, 2025 1:00pm - 1:50pm PDT

VIRTUAL DataWeek -- Main Stage

JJ Asghar, IBM, Developer Advocate

Honestly, you're probably jealous of those people saying "ChatGPT" is making their lives easier. You may think that leveraging AI is this generation's adoption of the calculator. I'm here to say yes, you are right, but let's be honest: we have no idea how the ChatGPTs of the world are trained or if they are secure.
If you run a technology company, your data is your secret sauce; if your boss found out you were leveraging ChatGPT to do your job, would they be happy? Probably not.
In this presentation, we will explore how LLMs work locally through hands-on activities, such as setting up some local open-source private and free LLMs to help you get closer to the promise of generative AI.
Overall, this presentation will start with some basic installation leveraging Ollama and VS Code or any of the JetBrains platforms (and you'll learn what that means and what the differences are!), then pull in AnythingLLM and/or OpenWebUI to help give you a straightforward chat-like interface to your LLM. We will provide you with the knowledge, tools, some generic prompts, and use cases to gain more confidence in your daily life by leveraging LLMs.
You'll walk out of the workshop with a working LLM that you can engage with no fees or usage, all locally and securely.

Speakers

JJ Asghar

Developer Advocate, IBM

JJ works as a Developer Advocate representing IBM worldwide. He mainly focuses on open-source AI and OpenShift, trying to help companies and users successfully onboard to the Cloud-Native ecosystem. He’s also known in the DevOps tooling ecosystem and generalized Linux communities... Read More →

Wednesday September 10, 2025 1:00pm - 1:50pm PDT
VIRTUAL DataWeek -- Main Stage

Additional Topics Generative AI, RAG & LLMs
Talk Type PRO Workshop Day (Wed)
Tracks DataWeek, AI Models and Management (DataWeek), Data Tools / Technology and Management (DataWeek), Virtual
In-Person/Virtual Virtual

2:00pm PDT

[Virtual] PRO WORKSHOP (DataWeek): From Data to Insights in Minutes: Accelerating Business Growth with AutoML and LLM-Powered Data Prep

Wednesday September 10, 2025 2:00pm - 2:50pm PDT

VIRTUAL DataWeek -- Main Stage

Shailaja Sampat, Fujitsu Research of America, Senior Researcher

- Are you tired of manually processing large datasets in spreadsheets? 
- Have you considered using Machine Learning (ML) to automate your tasks but feel limited by your coding skills or time constraints?
 - Looking for ways to reduce the time spent in making your data AI-ready, despite your ML background?

If these challenges sound familiar, this session is for you!

Traditionally, building predictive models has required specialized coding and statistical expertise. Moreover, data professionals often dedicate over 80% of their time to the labor-intensive data-wrangling process- to prepare raw data for consumption by automated machine learning (AutoML) tools. To overcome these hurdles, we introduce AutoDW, an innovative data wrangler that utilizes the power of Large Language Models (LLMs) and sophisticated automation to facilitate the seamless preparation of AI-ready data. This session will demonstrate how the synergistic application of AutoDW and AutoML empowers users to rapidly develop predictive prototypes for their business use cases end-to-end without writing any code. Through step-by-step instruction and a live demonstration, attendees will witness AutoDW's intelligent data processing, observe AutoML's autonomous algorithm selection tailored to specific applications, and, most importantly, gain a comprehensive understanding of how to interpret the resulting predictive outputs.

#AutoML #DataWrangling #NoCodeML #FastMLPrototyping #DataDrivenDevelopment

Speakers

Shailaja Sampat

Senior Researcher, Fujitsu Research of America

Shailaja Sampat is a senior researcher in the AI lab at Fujitsu's research division in the USA. She earned her Ph.D. from Arizona State University, with a thesis focusing on the intersection of natural language processing and computer vision. Her current research spans autoML, data... Read More →

Wednesday September 10, 2025 2:00pm - 2:50pm PDT
VIRTUAL DataWeek -- Main Stage

Additional Topics RAG & LLMs
Talk Type PRO Workshop Day (Wed)
Tracks DataWeek, Data Science and Machine Learning (DataWeek), Data Tools / Technology and Management (DataWeek), Virtual
In-Person/Virtual Virtual

9:30am PDT

[Virtual] PRO Session (DataWeek): Intelligent Automation of Data Engineering Workflows with LLMs

Thursday September 11, 2025 9:30am - 9:55am PDT

VIRTUAL DataWeek -- Main Stage

Manohar Sai Jasti, Workday, Analytics Engineer

I will share how I developed an AI-driven system to transform raw SQL into production-ready dbt models using Large Language Models (LLMs). By combining retrieval-augmented generation techniques with dbt’s semantic framework, I automated SQL refactoring, modularization, testing, and documentation. This approach accelerates data engineering workflows, reduces manual effort, and enables scalable, production-ready analytics pipelines. I will walk through the architecture, challenges faced during scaling, validation strategies for AI-generated SQL, and key lessons learned from deploying this solution in real-world environments. Attendees will gain practical insights into applying LLMs for data workflow automation, improving pipeline quality, and driving faster AI productionization across modern data stacks.

Speakers

Manohar Sai Jasti

Analytics Engineer, Workday

Manohar Sai Jasti is an experienced Analytics Engineer specializing in building efficient and scalable data pipelines. With expertise in tools like dbt, Trino, and cloud platforms, he helps organizations turn data into actionable insights. Manohar is passionate about simplifying data... Read More →

Thursday September 11, 2025 9:30am - 9:55am PDT
VIRTUAL DataWeek -- Main Stage

Additional Topics RAG & LLMs
Talk Type PRO Session
Tracks DataWeek, Data Engineering / Architecture and Streaming (DataWeek), Virtual
In-Person/Virtual Virtual

3:30pm PDT

[Virtual] OPEN Session (DataWeek): Balancing Velocity with Academic Rigor When Building with LLMs

Thursday September 11, 2025 3:30pm - 3:55pm PDT

VIRTUAL DataWeek -- Main Stage

Lauren Peate, Multitudes, CEO & founder

We’re all building AI features now. But building with LLMs brings its own challenges – namely: How can we use cutting-edge practices, weave in AI ethics, and consider the cost of different models without blowing past delivery dates. Not to mention making sure that the features we build will be stable, reliable and maintainable in the future.

We recently built our first LLM feature, to show the quality of feedback given in code reviews. In 1 month, we did a literature review, consultation with academic experts, data labelling, model experimentation, a cost assessment, and finally, all the ML engineering to launch it into production. The outcome: <1% extreme misclassification and zero hallucinations. In this talk, we’ll share our approach to building LLM features – how we partnered with academia (without being delayed by their timelines), what tooling we used, and how we made the cost and money tradeoffs to keep business stakeholders happy. I’ll also speak to how we built this into our microservices architecture, including how we used tools to generate structured outputs from LLMs on top of AWS’s Bedrock API to have parseable responses from a range of models.

You'll walk away with practical strategies for leading your own teams through AI implementations, identifying ethical issues early, addressing them efficiently, and still delivering on time and on budget.

Speakers

Lauren Peate

CEO & founder, Multitudes

Lauren Peate is the CEO and founder of Multitudes, which helps engineering teams improve delivery sustainably. She’s focused her career on using data to support people, including as the founder of Ally Skills NZ, a consultancy helping global tech companies improve team performance... Read More →

Thursday September 11, 2025 3:30pm - 3:55pm PDT
VIRTUAL DataWeek -- Main Stage

Additional Topics Microservices, RAG & LLMs, Privacy and Ethics
Talk Type OPEN Session
Tracks DataWeek, AI Models and Management (DataWeek), Data Science and Machine Learning (DataWeek), Virtual
In-Person/Virtual Virtual

10:00am PDT

[Virtual] PRO Session (DataWeek): Data Sovereignty in the Age of AI

Friday September 12, 2025 10:00am - 10:25am PDT

VIRTUAL DataWeek -- Main Stage

Michel Tricot, Airbyte, Co-founder and CEO

This session will explore the intersection of data sovereignty and artificial intelligence, addressing how organizations can maintain control of their valuable data assets while still leveraging the power of AI. Drawing from extensive experience building open-source data infrastructure solutions, Michel will illuminate the challenges companies face when integrating AI into their data ecosystems without compromising ownership, security, or compliance requirements.

The session targets data leaders, CDOs, and enterprise architects who are navigating the complex landscape of AI adoption while maintaining strict data governance standards. Michel will share practical frameworks for implementing a self-managed data integration strategy that enables AI innovation while preserving first-party data sovereignty—a crucial consideration as regulatory requirements around data protection continue to evolve globally. Attendees will gain actionable insights on building resilient data architectures that support AI initiatives without surrendering control of sensitive information.

This session aligns perfectly with Data Week's focus on "Data Engineering & Governance" and "AI & ML" tracks, offering attendees a unique perspective on balancing innovation with control. Conference participants will benefit from Michel's vision of how open-source data integration infrastructure can serve as the foundation for responsible AI development, empowering organizations to build competitive advantages while maintaining complete sovereignty over their data. The presentation will include real-world examples of companies that have successfully implemented these principles.

Speakers

Michel Tricot

Co-founder and CEO, Airbyte

Michel Tricot is co-founder and CEO of Airbyte, the open data movement platform. The company was started in 2020 with a vision of commoditizing data integration pipelines across all industries and organizations and today has more than 170,000 deployments. Michel has been working in... Read More →

Friday September 12, 2025 10:00am - 10:25am PDT
VIRTUAL DataWeek -- Main Stage

Additional Topics Integration Strategy, RAG & LLMs
Talk Type PRO Session
Tracks DataWeek, AI Models and Management (DataWeek), Data Engineering / Architecture and Streaming (DataWeek), Virtual
In-Person/Virtual Virtual

2:00pm PDT

[Virtual] OPEN Session (DataWeek): Transforming Seller Onboarding in Retail: Responsible AI, RAG, and Risk Management

Friday September 12, 2025 2:00pm - 2:25pm PDT

VIRTUAL DataWeek -- Main Stage

Banani Mohapatra, Walmart, Senior Manager, Data Science
Bhavnish Walia, Amazon, Senior Risk Manager AI/ML

Onboarding new sellers onto retail platforms like Walmart and Amazon involves a complex, multi-step process designed to mitigate fraud and ensure compliance with global regulations. One of the most critical and cumbersome steps is Know Your Customer (KYC) verification, requiring sellers to upload documentation for identity verification, business registration, and compliance checks. This manual review process often leads to long approval times and delays, frustrating legitimate sellers and creating operational bottlenecks for compliance teams.
To address these challenges, we leveraged foundational models with custom prompting strategies, in-document summarization, and retrieval-augmented generation (RAG) to ground responses in trusted data sources, powered by open-source LLM APIs. By automating document analysis and augmenting human reviewers with AI outputs, we reduced overall onboarding time by more than 20 percent, improving seller experience and operational efficiency.
However, deploying AI into a regulated process like KYC required a robust responsible AI framework combining scalability with governance. We implemented guardrail models to flag edge cases and ensure human oversight, enforced strict data anonymization protocols to protect sensitive information, and applied privacy-preserving techniques for model training. We also established a rigorous validation pipeline to test outputs against regulatory standards, mitigating risks such as hallucinations and interpretability gaps.
This talk offers actionable insights for data scientists, compliance officers, regulators, and machine learning practitioners working at the intersection of AI, risk management, and regulatory compliance. Presented by Bhavnish Walia, Senior Risk Manager at Amazon, and Banani Mohapatra, Senior Data Science Manager at Walmart, attendees will walk away with a practical framework for deploying AI in sensitive domains—covering risk management strategies, scalable AI architectures aligned with compliance, and key lessons on balancing innovation with accountability.

Speakers

Bhavnish Walia

Senior Risk Manager AI/ML, Amazon

Bhavnish Walia is a Senior Risk Manager at Amazon, where he leads AI Risk Management efforts focused on developing large language model (LLM) frameworks for data governance and regulatory compliance. He ensures the safe and compliant deployment of AI systems at scale. With over 12... Read More →

Banani Mohapatra

Senior Manager, Data Science, Walmart

Banani Mohapatra is a data science leader with 12+ years of experience in e-commerce, payments, and real estate, specializing in machine learning, generative AI, LLMs, and causal AI. She leads a global data science team at Walmart, driving subscription growth with multi-billion-dollar... Read More →

Friday September 12, 2025 2:00pm - 2:25pm PDT
VIRTUAL DataWeek -- Main Stage

Additional Topics AI/ML, Retail, RAG & LLMs, Privacy and Ethics
Talk Type OPEN Session
Tracks DataWeek, OPEN Session, Data Governance and Security (DataWeek), Virtual
In-Person/Virtual Virtual