Hey, I'm Sam 👋 — a #software-engineer working on #ai-pipelines, #backend and the #cloud-infra that ships them.
For the past year and a half that's meant one AI platform, end to end: the video-generation pipeline, the APIs around it, the billing, the GPU workers, and the deploys.
I write Python most days, C# and TypeScript when the problem calls for it. What I actually optimize for is failure:
- A provider dying mid-render shouldn't lose the job.
- A refund should go back exactly where the money came from.
- A deploy should never drop a request.
- Most of my work is making those sentences stay true.
I got into software through game development — years of Unity and VR/AR — and I still think in frame budgets and edge cases.
👀 Two from the top of the pile — the rest live in #work.
A durable ~20-step generation pipeline that sleeps on webhooks and never loses state.
Multi-provider failover that cut video-generation failures by more than half.
Vocal removal and video inpainting with model weights baked into the image.