Samuel Abiodun

Software / AI Engineer — backend, LLM pipelines & the infra to ship them

I'm a backend engineer working on AI products. For the past year and a half that's meant one 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, and 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.

GitHub LinkedIn Email
Recently shipped

AI Video Generation Pipeline

Sandwatch · 2026

Primary engineer on the video-generation service — a dedicated service we extracted the generation logic into and rebuilt on Inngest. It's a ~20-step durable pipeline spanning script, voice, character, and multi-stage visual generation; each step suspends until its provider webhook fires, so a job can wait on a render as long as it needs and resume exactly where it left off without tying up a worker or losing state on a restart. Also built the quality layer: a promptfoo harness with a multimodal judge that watches the rendered .mp4 and scores it.

PythonInngestFastAPILLM gatewayStructured outputpromptfooLLM-as-judgeEvals

Video Generation — Provider Fallbacks

Sandwatch · 2026

Video providers go down or reject jobs constantly, so I turned a single-provider call into a multi-provider fallback chain that treats a terminal poll response as failure, reorders providers on failure, and skips flaky ones inside a bad time window. Adding a fallback provider dropped the failure rate by more than half and cut average generation time. Added an upscaling pass and an automated suite so the logic can't silently rot.

PythonMulti-providerResilienceFallbacksUpscalingTesting

→ all projects