AI/ML Platform Engineer in Boston. I build production AI systems, streaming data platforms, and the MLOps glue between them.
Boston, MA · AI/ML Platform Engineer · 8+ yearsShipped Kafka pipelines at 10M+ events/day, low-latency inference for 1M+ daily orders, and TB-scale data platforms across UKG, Dunzo, and Warpspd. Now open-sourcing the AI platform tools — eval, observability, cost-aware routing, NL→SQL, and a modern data stack — I keep rebuilding at every job.
I’m an AI/ML Platform Engineer who likes shipping the unglamorous parts: the APIs, feature pipelines, evaluation harnesses, and deployment paths that make AI products reliable once people actually use them.
Open-source tools across the LLM lifecycle — evalstack gates, tracelens observes, routerai governs — plus RAG NL→SQL and a modern data stack. All MIT-licensed, self-hostable, and demo-able locally with one docker compose up.
Open-source LLM evaluation framework — Python SDK + CI plugin, LLM-as-judge rubrics, regression detection, side-by-side run + event diff. Gates prompt/model changes in CI before they ship. Braintrust alternative.
Alpha · Demo liveNatural-language analytics for founders + PMs — schema-aware, RAG-grounded, sqlglot-safety-gated SQL generation against DuckDB. EXPLAIN-based cost preview, single-page chat UI, key-free demo mode.
Production LLM observability — one decorator to instrument, then a failure-path breakdown (rate_limit / timeout / connection_error) plus latency + cost per model. FastAPI collector, pluggable storage (SQLite or ClickHouse), p50/p95/p99 dashboard. Auto-detects OpenAI + Anthropic response shapes.
Alpha · Demo liveCost-aware LLM routing gateway — routes each request to the cheapest model that clears a quality bar, with shadow-eval and savings metrics. The "govern" control plane that completes the trilogy: evalstack gates, tracelens observes, routerai governs.
Real-time feature store you can deploy in a day — declarative YAML feature defs drive a recompute-on-write pipeline into DuckDB (offline, Parquet-exportable) and a pluggable online store (in-memory or Redis). Feast/Tecton alternative for teams without weeks to spend on deployment.
MVP · Working end-to-endEnd-to-end open-source data platform template — the feature-engineering backbone under ML/AI systems. Postgres → Debezium / snapshot CDC → Iceberg-style Parquet → dbt (bronze/silver/gold) → DuckDB queries. Single make demo runs the full path.
