Worked on a hybrid retrieval stack combining vector similarity, graph traversal, and keyword search. Built the benchmarking pipeline that scored the system against the LongMemEval and LoCoMo papers, the two canonical long-context memory benchmarks, and turned the results into the signal the team used to decide what to ship next.

Built the product end to end as the only engineer. LangGraph agents orchestrating outbound research and outreach, async workers, real-time dashboards, human-in-the-loop review for every generated message, and a Next.js app on top. Owned the infrastructure, the prompts, the evaluation, and the design.

The most useful thing I learned in that year was how fast a LangGraph stack accumulates cost and reliability debt when nobody is watching. Most of my current writing is downstream of that observation.

Ran five engineering teams, thirty-five plus engineers reporting through me. The core piece of work was rebuilding the entire payment workflows and pricing models end to end, which brought processing errors down by 40%.

Around this time I started the Berkeley ML/AI postgrad, which is what eventually pulled me back into hands-on building.

Joined as a senior engineer, ended as a manager running a product-area team. Useful stretch, because I got to do the transition inside a single company.