I own products end to end — React & TypeScript up front, Node & Django behind them, and the AI systems on top: live voice agents, RAG pipelines, and automations that turn incidents into merged pull requests.
Latest launch
Live Job-search prep in one calm place: honest resume tailoring, cited company research, and live voice AI interviews that adapt, push back, and score you. Maeve remembers every session. 4,800+ interviews completed in early access.
View →Selected work
Agent systems
Not demos. Systems handling real traffic, real money, and real clinical data — with guardrails, evals, and monitoring.
Goose agents reproduce incidents and open ready-to-review PRs. 30+ tickets a month, hands-off.
User-reported bugs scoped, fixed, and drafted as PRs by agents. Engineers review and merge.
Takes real actions inside the product via tool calls — permissions, guardrails, structured outputs.
Clinical, support, and internal knowledge pipelines. pgvector, eval-driven iteration, ~40% latency cut.
Experience
Senior Full-Stack Engineer
TypeScript · Node.js · Django · AWS Lambda · React · LangChain · Goose · Inngest · LiveKit · Deepgram
Full-Stack Developer
Python · OpenAI · FastAPI · PostgreSQL · React · AWS Lambda
Full-Stack Developer
Node.js · React · Flask · PostgreSQL · MongoDB · TensorFlow
Stack
Writing
Interview prep is full of question banks and resume puffery. Almost nothing simulates the actual conversation. Here's the gap I kept seeing — and the product I shipped to close it.
If the only way you know your AI feature works is that it felt right in the demo, you do not actually know it works. Here is how to start measuring.
The skill that matters is not wording a clever prompt. It is deciding what goes in the context window, what stays out, and in what order.
Open to senior full-stack and applied AI roles — or conversations about agents, RAG, and product engineering at scale.
