Join us as we explore
GenAI Engineering: One Line at a Time
At Comet’s Annual Convergence Conference
Virtual Event | May 13th -14th, 2025
+ Networking Reception, San Francisco
2
Days of content
25
+
Speakers
3,500
+
Attendees online
As the industry transitions from traditional machine learning to generative AI, new challenges unique to LLMs are emerging. Convergence 2025 provides a platform to explore these shifts, with sessions on advanced LLM evaluation techniques, the potential of agentic AI, and the responsible use of generative AI. Join us to dive into the complexities of building and deploying LLM-based applications, and connect with others shaping the future of this rapidly evolving field.
About Convergence
The fourth edition of Comet’s Convergence Conference on May 13-14, 2025 will navigate GenAI Engineering: One Line at a Time. This two-day virtual event features over 25 expert-led sessions, including in-depth talks, technical panels, and interactive workshops. Connect with our global community at a networking reception in San Francisco. Engage with leading ML developers, data scientists, and industry experts as we address the latest developments in LLM technology and its significant impacts on AI. Be at the forefront of shaping an ethical and advanced AI landscape.
Two Days x Two Talk Tracks
We’re excited to offer two different tracks for Convergence 2025! Choose the track that best fits your interests and experience, or mix and match sessions from each!
Track 1: GenAI Foundations
For those learning how to build reliable GenAI systems,
one line at a time.
Learn the fundamentals of building GenAI systems—from architecture and optimization to debugging and evaluation. This track dives into the mechanics behind reliable LLM-powered apps, with practical, technical talks on RAG, evals, agents, and more.
Track 2: GenAI in Practice
For those looking to go beyond the fundamentals
and into the field.
Explore real-world GenAI applications and learn from the engineers and leaders deploying them as they share how they scale infrastructure, address safety and evaluation challenges, and navigate edge cases and changing regulations.
Speakers
Hugo Bowne-Anderson
Data Science Educator
& Vanishing Gradients Host
Albert Lie
Co-Founder at Forward Labs
Allegra Guinan
Co-Founder & CTO at Lumiera
João Moura
CEO at CrewAI
Tony Kipkemboi
Sr. Developer Advocate at CrewAI
Tharun Tej Tammineni
Staff Partner Engineer at Meta
Jeremy Mumford
Lead AI Engineer at Pattern
Jasleen Singh
Senior Principal Software Engineer at Dell Technologies
Sawan Ruparel
VP of Engineering at Boston Consulting Group X
Nikhil Kassetty
Senior Software Engineer at Intuit
Alex Shershebnev
ML/DevOps Lead at Zencoder
Carolyn Olsen
VP of Data Science at Clearcover
Gideon Mendels
CEO & Co-Founder at Comet
Doug Blank, Ph.D.
Head of Research at Comet
Vincent Koc
Lead AI Researcher Engineer & Developer Relations at Comet
Paarth Chothani
Staff Software Engineer at Uber
Xandra Zhu
Machine Learning Engineer at Uber
Jonathan Li
Software Engineer at Uber
Kailash Thiyagarajan
Senior Machine Learning Engineer at Apple
Parker Duckworth
Director of Database Engineering at Weaviate
Ram Ganesh
Senior Data Scientist at Mastercard
Rajarshi Tarafdar
Senior Software Developer-GenAI at JP Morgan Chase
Leonardo Gonzalez
VP of AI Center of Excellence at Trilogy
Paul Iusztin
Senior AI Engineer/ Founder at Decoding ML
Schedule
Day 1 | Tuesday May 13
12:00PM ET
INTRODUCTION
12:05PM ET
Escaping Demo Hell: Shipping Responsible AI from Prototype to Production with Eval-Driven Development
Track 1: GenAI Foundations
Albert Lie – Co-Founder at Forward Labs
12:05PM ET
Evaluation-Driven Development: Building Reliable AI Systems
Track 2: GenAI in Practice
Hugo Bowne-Anderson – Data Science Educator and Vanishing Gradients Host
12:35PM ET
Crafting Effective Agents – From Design to Observability
Track 1: GenAI Foundations
Tony Kipkemboi – Senior Developer Advocate at CrewAI
Practical Approaches to Building Safer AI Systems
Track 2: GenAI in Practice
Allegra Guinan – Co-Founder & CTO at Lumiera
1:05PM ET
AI Coding Agents and How to Code Them
Track 1: GenAI Foundations
Alex Shershebnev – ML/DevOps Lead at Zencoder
1:05PM ET
Simpler, Faster, Better: Challenging GenAI Implementation Assumptions
Track 2: GenAI in Practice
Carolyn Olsen – VP of Data Science at Clearcover Insurance
1:35PM ET
Scaling Intelligence: Engineering Challenges Behind Vector Databases in the Age of AI
Track 1: GenAI Foundations
Parker Duckworth – Director of Database Engineering at Weaviate
1:35PM ET
You Don’t Train for a Marathon in a Lab
Track 2: GenAI in Practice
Sawan Ruparel – Vice President of Engineering at BCGX
2:05PM ET
15 MIN BREAK
2:20PM ET
A Panel Discussion: The Rise of AI Agents: From Demos to Deployment
Gideon Mendels – CEO at Comet
Tharun Tej Tammineni – Senior Partner Engineer at Meta
Jeremy Mumford – Lead AI Engineer at Pattern
João Moura – CEO at CrewAI
3:05PM ET
From Hallucination to Accuracy: Evaluating Context Retrieval in RAG Systems
Track 1: GenAI Foundations
Jasleen Singh – Senior Principal Software Engineer at Dell
3:05PM ET
Uber’s Oncall Copilot Accuracy Journey
Track 2: GenAI in Practice
Paarth Chothani – Staff Software Engineer at Uber
Xandra Zhu – Machine Learning Engineer at Uber
Jonathan Li – Software Engineer at Uber
3:35PM ET
15 MIN BREAK
3:50PM ET
Smaller, Smarter, Sustainable: Optimizing LLM’s by Leveraging White Box Knowledge Distillation Algorithms
Track 1: GenAI Foundations
Ram Ganesh – Senior Data Scientist at Mastercard
3:50PM ET
AI-Powered Payment Gateways for Green Finance: Using LLM Agents to Drive Sustainable Transactions
Track 2: GenAI in Practice
Nikhil Kassetty – Senior Software Engineer – AI and Fintech Expert at Intuit
4:20PM ET
Optimizing Large Language Models: Techniques for Efficiency and Performance
Track 2: GenAI in Practice
Kailash Thiyagarajan – Senior Machine Learning Engineer at Apple
4:20PM ET
Optimizing LLM Performance: Scaling Strategies for Efficient Model Deployment
Track 1: GenAI Foundations
Rajarshi Tarafdar – Senior Software Engineer at JP Morgan Chase
4:50PM ET
DAY 1 WRAP UP
Day 2 | Wednesday May 14
12:00PM ET
INTRODUCTION
12:00PM ET
Workshop | LLM & RAG Evaluation Playbook for Production Apps
Paul Iusztin – Senior AI Engineer / Founder at Decoding ML
1:00PM ET
15 MIN BREAK
1:15PM ET
Workshop | Precision Prompting: Tuning LLM Performance Through Algorithmic Optimization
Vincent Koc – Lead AI Research Engineer at Comet
1:45PM ET
Workshop | Smarter Prompting, Faster: Introducing Opik’s Agent Optimizers
Doug Blank, PH.D. – Head of Research at Comet
2:45PM ET
15 MIN BREAK
3:00PM ET
Workshop | Navigating Uncharted Metrics: Reference-Free LLM Evaluation with G-Eval
Leonardo Gonzalez – VP of AI Center of Excellence at Trilogy
4:25PM ET
DAY 2 WRAP UP
Some Participating Companies
Some Topics Covered
Federated Machine Learning
AI Governance
Diffusion Models
Scalability and LLMOps
LLM Security
Vector Databases/Search
LLMs in Production
Vision Transformers
Multilingual LLMs
Model Pruning &
Why Attend Convergence?
Attending Convergence is the perfect opportunity to be at the forefront of GenAI Engineering. For ML professionals, this annual conference offers a deep dive into the technical intricacies of LLMs, equipping you with the latest tools and methods in prompt engineering and LLM evaluation. Software Engineers entering the field will find accessible sessions that provide the foundational knowledge necessary to start building and deploying generative AI applications effectively. It’s an essential platform for those looking to enhance their expertise, keep pace with rapid advancements in AI, and contribute to the ethical development of new AI technologies.
Register for Convergence 2025
Registration is now closed