Loading…
Subject: Data Science and Machine Learning (DataWeek) clear filter
arrow_back View All Dates
Thursday, September 4
 

11:30am PDT

OPEN Session (DataWeek): Strategies for Image Dataset Curation from High-Volume Industrial IoT data
Thursday September 4, 2025 11:30am - 11:55am PDT
Apurva Godghase, Brambles, Senior Computer Vision Engineer

In Industrial IoT for Supply chain, and logistics, massive amounts of data is generated by edge devices that capture data continuously. For embedded vision systems, managing the sheer volume of images and metadata can be challenging. Selecting a diverse subset of high-quality data is crucial for effective modeling and analysis. This work outlines a comprehensive method for selecting relevant images from an extensive dataset to build a high-quality image database for building and monitoring computer vision and machine learning models. This systematic approach not only enhances the efficiency of data management in industrial IoT applications but also improves the generalizability and accuracy of Computer Vision learning models. 
Speakers
avatar for Apurva Godghase

Apurva Godghase

Senior Computer Vision Engineer, Brambles
Apurva is a Senior Computer Vision Engineer at Brambles, with over seven years of R&D experience across diverse industrial domains. At Brambles, she specializes in designing and deploying cutting-edge machine learning and computer vision IoT prototypes to enhance supply chain efficiencies... Read More →
Thursday September 4, 2025 11:30am - 11:55am PDT
DataWeek -- Main Stage

2:30pm PDT

KEYNOTE (DataWeek): Informatica -- Mastering Enterprise AI Agents: Best Practices for Multi-Agent Frameworks
Thursday September 4, 2025 2:30pm - 2:55pm PDT
Sumeet Kumar Agrawal, Informatica, Vice President Product Management

Explore the design and deployment of enterprise-grade AI agent systems. This session covers best practices for building scalable multi-agent frameworks, ensuring security and governance, and features real-world examples from industries like customer service and supply chain management. Learn how to integrate AI agents effectively while addressing key enterprise challenges. 
Speakers
avatar for Sumeet Kumar Agrawal

Sumeet Kumar Agrawal

Vice President Product Management, Informatica
Sumeet Agrawal is the Vice President of Products at Informatica, where he spearheads product management of innovative cloud-based technology products. With over 15 of experience in data engineering and product management, Sumeet has a proven track record of driving innovative solutions... Read More →
Thursday September 4, 2025 2:30pm - 2:55pm PDT
DataWeek -- Main Stage

3:30pm PDT

OPEN Session (DataWeek): Balancing Velocity with Academic Rigor When Building with LLMs
Thursday September 4, 2025 3:30pm - 3:55pm PDT
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
avatar for Lauren Peate

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
 

Share Modal

Share this link via

Or copy link

Filter sessions
Apply filters to sessions.
Filtered by Date -