AI Systems Engineer
I build the layer that makes AI features cheap and safe to ship — LLM runtimes, governed agent platforms, and the retrieval underneath.
$ focus --on llm-runtimes, agents, semantic-search, prod-infra
Most recently: a governed agent runtime taken from an empty repository to two authorized staging deployments in five weeks, solo — 99K lines, 223 routes, 1,453 tests, and a human approving every consequential write. Open to senior and founding AI engineering roles.
Contract-driven agent runtime rebuilt from an empty repository to two authorized staging deployments in five weeks, solo: 98,896 lines, 223 HTTP routes, 1,453 tests, 68 typed operator contracts behind a single policy-enforcing gateway, SSE streaming, and a human approval gate on every consequential write.
One generic spider replaces N hand-written ones: an LLM reads a page's DOM digest and emits a crawl plan, which is statically linted, dry-run against the live site, and auto-repaired before anything runs. 64,572 researcher records across 143 institutions in 7 countries, at roughly CAD 0.03 per record.
Apache-2.0 async runtime kernel for LLM and agent applications: 45,598 lines across 95 modules, 492 tests, 17 documented stable API namespaces under a published five-tier stability policy. Built deliberately instead of adopting LangChain.
Research-stage learnable scoring layer that separates access frequency from semantic salience in LLM memory systems — the failure mode that causes drift and recall failures in Mem0, Letta, and Zep on long-horizon tasks.
A hybrid localization approach combining vision transformers with traditional geometric methods for robust self-localization of humanoid robots in RoboCup competition environments.
Comprehensive compilation and quality assessment of street-level urban air temperature measurements across European monitoring networks, published in Scientific Data (Nature Portfolio).
LLM / Retrieval / Search
Governance & Reliability
Backend & Systems
AI / Machine Learning