Senior AI Engineer
IIT-BHU · UC Berkeley · Microsoft · Osmo · Epic! · Knit
I turn messy human workflows into reliable, observable AI software across LLM orchestration, evaluation, analytics, deck automation, ML infrastructure, search, and computer vision.
Systems I shipped
Knit · May 2025 – April 2026
Architected a production agentic research workflow that transformed analyst-heavy reporting into a verified AI execution pipeline.
Epic! for Kids · February 2023 – May 2024
Took ownership of production ML systems after layoffs and reduced cost, complexity, and operational risk.
Tangible Play / Osmo · September 2019 – February 2023
Led CV systems that improved worksheet recognition accuracy and supported interactive learning workflows.
Writing
Autonomy works better when a system exposes state, retries, artifacts, and ownership boundaries instead of hiding them inside a chat transcript.
Routing, retry budgets, cache boundaries, and judge coverage are user-experience choices when they decide whether a workflow can run reliably.
A valid JSON object can still answer the wrong question. Evaluation has to cover intent, provenance, and the artifact a user will trust.
Decision theater
Staff-level judgment shows in trade-offs, not just outcomes.
Decision fork
The workflow needed parallel execution and reliable recovery, not just autonomous behavior.
Chosen: Explicit DAG orchestration. Production workflows need predictable execution and debugging more than theatrical autonomy.
Contact
I am best matched with senior AI/platform and LLM systems roles where reliability, evals, observability, and cost matter.