Boring Workflows. Early-stage, four people, no playbook. I owned the architecture, the AI, the infra, and the demo. Whatever needed to exist, I built it.
"The architecture decision I'm most proud of isn't the one I made — it's the one I talked us out of. We saved three weeks by not building the wrong abstraction."— On a SWARM refactor that didn't happen
Most "multi-agent" projects are two LLM calls in a trenchcoat. SWARM runs each agent in its own Kubernetes pod, spawned on demand, wired to real enterprise systems — Jira, Outlook, internal ticket queues. Ticket triage, email routing, network fault resolution.
Telcos blast the same SMS to 100,000 people and call it personalisation. AutoCLM is the alternative — continuous 1:1 WhatsApp conversations, each customer on their own AI-planned journey arc. Built the full stack: backend, WhatsApp integration, team-facing dashboard, and five realistic customer personas for demo.
"Close enough" isn't acceptable when an AI is quoting plan prices to real customers. I scrapped v1 and rebuilt — hybrid dense+BM25 retrieval, RRF fusion, Cohere reranking, LLM-generated chunk labels. Four content zones, approval loop for all ingested data, soft deletes only.
A retrieval system for insurance policy documents — the kind of dense, jargon-heavy text where standard chunking falls apart. Built to answer real coverage questions accurately, not confidently-wrongly.
Built a distributed system in Go to learn gRPC and GraphQL properly — not a tutorial clone, but something with real service boundaries, protobuf contracts, and an API gateway. The kind of project you build when you want to understand the seams.
Merged PRs on real codebases — features, fixes, and reliability — not drive-by typo PRs for green squares. Every repo below reviewed my code against engineers worldwide.
A production AI agent codebase used by developers worldwide — CI on Linux and macOS, real code reviews, engineers from across the ecosystem. 15+ merged PRs, not one-liners.
I don't need a title or a large team. I need a problem worth solving and room to solve it properly. If that's where you are, I want to hear about it.