Maitrik Patel
Engineering and Product Leader | AI/ML • Web • Design
San Francisco, California, United States
Actions
A data-driven engineering and product leader, I architect efficient, intuitive, and scalable systems by integrating AI, web, and design principles. I empower high-impact teams to deliver AI-powered tools used by millions, transforming how products are developed and experienced. My vision is to shape the future of consumer AI—where intelligent systems drive meaningful, lasting impact and make everyday experiences smarter, more productive, and more human.
Links
Area of Expertise
Topics
Synthetic Lives for Smarter Agents: Generating Personal Context Data for AI Benchmark Design
Building benchmarks for personal AI agents requires something that doesn't naturally exist: large-scale, coherent personal context data. Real user data is private. Randomly generated data lacks the internal consistency of real human lives.
For ASTRA-bench, we developed an event-driven synthetic data generation pipeline to solve this problem. Rather than generating isolated data points, we grounded all synthetic data in longitudinal life events - biography, social network, and pattern of life - for four distinct protagonists. These events then propagated into multi-source personal context: emails, calendars, messages, notes, and preferences that are causally coherent with each other.
The generation itself used an agentic LLM workflow to produce 2,413 scenarios that span weeks and months of protagonist life, enabling time-evolving context that single-snapshot benchmarks cannot capture. The result: synthetic personal data realistic enough that state-of-the-art models including Claude 4.5 Opus and DeepSeek V3.2 show significant performance degradation when reasoning over it.
One Orchestration Layer for All: Running ML, AI, and Agent Workflows
Most teams treat ML pipelines, AI batch jobs, and agent workflows as three separate infrastructure problems. They run ML training on one platform, AI inference on another, and emerging agent workflows on a third hastily-assembled stack. The fragmentation creates real cost: duplicated tooling, inconsistent observability, and infrastructure that cannot evolve as fast as the workloads on top of it.
This talk shares how we built a single unified orchestration layer to handle ML training, AI inference pipelines, and agent workflows at consumer scale - serving hundreds of millions of users downstream.
The first half walks through the architectural decisions: why a single orchestration layer wins over fragmented tooling, the type-safe task interfaces and container-native execution patterns that gave us the reliability guarantees production AI demands, the tradeoffs between adopting open-source workflow systems versus building proprietary tooling, and what we had to design on top of standard workflow primitives to handle non-deterministic agent execution that static ML pipelines never encounter.
The second half covers the production evolution: how the same infrastructure that originally served ML training jobs now routes and manages agent workflows in production. We cover the new failure modes that emerge with agent workloads, the retry strategies that broke down and what replaced them, the observability patterns required when execution paths are non-deterministic, the cost and resource scheduling implications, and the architectural patterns that make agent orchestration fundamentally different from pipeline orchestration.
Attendees leave with a concrete blueprint for designing a unified orchestration runtime for ML, AI, and agent workloads, an honest account of where this approach struggles, and a clear-eyed view of where the broader infrastructure ecosystem needs to evolve next.
Leading Engineers Through the AI Era: A Manager's Playbook for Real Team Adoption
Every engineering manager faces the same question: how do you help your team genuinely thrive in the AI era? Not just adopt the tools, but build the workflows, habits, and shared knowledge that turn AI-augmented engineering into actual productivity.
This is a practical, manager's-eye account of leading a team through real AI adoption. It focuses on what works.
Three patterns. First, the signals worth tracking versus the activity metrics that game themselves. Second, building a team second brain in Obsidian, a shared knowledge base where prompts, agent recipes, and lessons accumulate, turning individual experiments into team capability that grows as the team grows. Third, how the manager's role evolves as engineering shifts toward AI-augmented and agent-coordinated workflows.
Attendees leave with concrete patterns they can apply Monday morning, a starter template for a team second brain, and a productive lens on the leadership challenges of this transition.
Maitrik Patel
Engineering and Product Leader | AI/ML • Web • Design
San Francisco, California, United States
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top