talks · 2026
Taking production AI to the stage.
In 2026 I took the hard part of applied AI to three New York stages - not the demo, but making it run reliably, cheaply, and at scale.
Scaling Production RAG Systems with Kubernetes
How retrieval-augmented generation earns its uptime: autoscaling vLLM, vector search, and observability on Kubernetes so a RAG system stays fast and affordable when traffic stops being a benchmark and starts being real.
Real-Time AI Pipelines at Scale: Embedding LLMs into Apache Beam
Bringing LLM inference and RAG inside the pipeline itself - embedding models directly into Apache Beam transforms so streaming data can reason in real time, delivering low-latency intelligence on high-velocity data without ever leaving the stream.
From RAG to Agents
What AI already does for blockchain, and what has to be true before we let it act: retrieval that reads the chain and answers in plain English with its sources, models that watch transactions and read contracts before they ship, and agents that move money only inside limits the system enforces.
Hiring for AI or ML?
I am open to AI/ML Engineering, Data Science, and Python roles, plus research collaborations and consulting. New York based, shipping worldwide.