Software & AI Engineer
Eight years building production systems end-to-end across backend, frontend, and cloud infrastructure. Currently focused on LLM tooling, RAG, and agentic / multi-agent systems.
View Work →ABOUT me
Software engineer with 8 years shipping production systems across healthcare AI, biotech, and enterprise. My work spans backend APIs, React frontends, LLM-integrated pipelines, and the cloud infrastructure underneath — taking complex systems end-to-end.
Most recently at PictorLabs.ai — a UCLA spinoff in digital pathology — fine-tuning Google's PathFoundation vision model for automated stain-type detection, building LLM tooling with Claude API and LangGraph, and leading delivery of ClearStain, an AI virtual H&E staining pipeline for whole slide images.
I'm at my best where AI engineering meets real production engineering — training pipelines, retrieval systems, API design, and the infrastructure that holds it all up. Engineering fundamentals first, frameworks second.
Production systems end-to-end
AI fundamentals from first principles
Product, infra, and model pipelines
WORK history
SELECTED work
Codebase reasoning engine that turns any GitHub repository into an interactive, navigable knowledge surface — natural-language Q&A with source citations, on-demand Mermaid diagrams (architecture / class hierarchy / call graph), and three-phase agent-generated concept tours. Every stage of the AI pipeline is visible to the user in real time. Underneath: a production ReAct agent with 12 MCP tools, working memory, and parallel async tool execution, sitting on a hand-rolled retrieval pipeline (tree-sitter AST chunking, contextual LLM descriptions per Anthropic's pattern, Qdrant hybrid search with RRF, Cohere reranking, HyDE + query expansion). Every layer built from scratch — no LangChain, no LlamaIndex.
AI virtual H&E staining pipeline for unstained brightfield whole slide images at PictorLabs.ai (UCLA spinoff, venture-backed). Led delivery of a major new undertaking — integrated a new staining model end-to-end into the existing VSH (Virtual Slide Hub) system. Fine-tuned Google's PathFoundation vision model in PyTorch for automated stain-type detection feeding the validation pipeline. Owned Django API routing (organ / species / diagnosis-based predictor selection), Kafka job orchestration, and TorchServe model-serving integration.
Closed-source · proprietaryRAG system for querying research papers — grounding answers in document content with full source citations. Custom semantic search (MiniLM embeddings + ChromaDB), BM25 keyword search, and hybrid retrieval via RRF fusion. No LangChain. Precursor to Cartographer — built to understand retrieval internals from first principles.
View project →Full encoder-decoder transformer implemented in PyTorch — multi-head attention, positional encoding, layer norm, greedy decoding, label smoothing, LR warmup. Trained EN→ES on the Opus Books dataset, end-to-end from "Attention Is All You Need".
View project →Q-learning, DQN (Breakout), and PPO (LunarLander) trained on Gymnasium with Stable Baselines 3 — plus a custom multi-agent dual-taxi environment built from scratch (observation space, reward shaping, training loop). Domain breadth: not just LLMs.
View project →TECH stack
If you're building production AI or full-stack systems and want someone who can take it from architecture to shipped product — reach out.