ML infrastructure and AI solutions engineer. Currently supporting GPU clusters (H100s) on Kubernetes at a stealth startup. Previously at Weights & Biases. MS in AI from Penn State, BS in Statistics from UCLA.
I like building things end-to-end — from multi-agent RAG pipelines to custom K8s operators to full-stack dashboards.
| Project | What it does | Stack |
|---|---|---|
| Atlas AI · Live | Clinical intelligence platform — query patient records in natural language via a 3-node multi-agent RAG pipeline with 20+ medical tools | LangGraph, FastAPI, Next.js, pgvector, AWS Bedrock, ECS, RDS, Ollama |
| Atlas AI MCP | MCP server exposing healthcare AI tools for RAG-powered clinical queries, document reranking, and FHIR data ingestion — published on PyPI and Smithery | Python, MCP |
| Corium | Kubernetes operator with 3 custom CRDs for automated metrics collection, threshold alerting, and a monitoring dashboard | Go, Kubebuilder, Prometheus, Grafana, Next.js |
| JaxStats | Game performance analyzer with XGBoost ML scoring, 8-metric GPI breakdown, AI coaching, and live game overlays | FastAPI, XGBoost, React, Chart.js, Ollama |
| Aphae | AI agent office simulation — procedurally generated personalities (Big Five), emergent relationships, LLM-driven conversations, and a RimWorld-inspired drama director | Godot 4, GDScript, Ollama |
Languages Python Go TypeScript GDScript SQL C++
ML / AI PyTorch XGBoost LangGraph LangChain Hugging Face Ollama Bedrock MCP Ray
Infrastructure Kubernetes Kubebuilder Docker SLURM AWS ECS DynamoDB Helm Prometheus Grafana
Web FastAPI Next.js React Chart.js PostgreSQL pgvector