Experience
- Jan 2025 to present
Lead AI Product Engineer, Contract
Senior Product Engineer, Feb 2023 to Jan 2025
- Moved the team’s coding onto shared remote servers, so every engineer and agent works in the same setup.
- Built a shared context that loads for every engineer and updates itself from anyone’s work session.
- Built the team’s AI workflow on open-source skills, with our own add-ons and updates on top.
- Built a review agent that reads every pull request, makes the fixes it needs and works from the same shared context.
- Kept agent use safe and on budget with token limits, tiered tool access and secrets the model never sees.
- Feb 2022 to Feb 2023
Sr. Software Developer, DigitalSalt
- Took Hedged from first commit to launch in 5 months with four engineers, on web, iOS and Android.
- Cut latency 25% across Postgres, Redis and RabbitMQ on services handling ~1.5M requests a day.
- Built the monorepo behind 8 apps and the UI library 12 engineers use, and cut build times 40%.
- Architected zero-downtime releases for Docker services on ECS with EC2.
- Mentored 3 engineers and sat in on 10+ hiring interviews.
- Aug 2021 to Feb 2022
Frontend Developer, AppOctet
- Built client web and mobile apps with React, Next.js and React Native.
- May 2018 to Jun 2021
Software Developer, ToggleHead
- Built full-stack web apps for clients on React, Node.js, Express and MongoDB.
How I work with AI
More on this- Meetings become ticketsThe agent preps my syncs from merged work and turns call transcripts into tickets.
- No code without a specIt questions me until a feature is clear enough for someone else to build.
- Agents build in parallelEach ticket gets its own agent, copy of the repo and full brief.
- Two reviews, then my callOne checks my standards, the other the plan. Merging stays with me.
- Busywork starts as a draftStatus updates, email replies and commit messages come from the agent.
- Every session teaches the nextMemory keeps my preferences, and a mistake that repeats becomes a rule.
Selected work
- Mosaic AIAn analyst for healthcare data that answers plain-English questions with guarded SQL over live Snowflake.Case study
- PerpetuityA real-estate deal platform where an LLM reads the documents and people approve every number.Case study
- HedgedTrading guidance for investors, launched on web, iOS and Android and past 100k installs today.Case study
Now
- Learning
- DevSecOps from the attacker’s side.