About
I'm an AI engineer. I build systems end-to-end — RAG pipelines, multi-provider LLM orchestration, and conversational agents processing thousands of updates daily — and I own them from architecture and evaluation through deployment, monitoring, and cost tracking.
Two backgrounds make me better at it:
- Data analytics taught me rigour. Don't trust a number until you know where it came from, measure against a baseline, and notice when a metric is quietly lying — which is most of what evaluating an LLM system really is.
- Full-stack development taught me ownership. The model is one part of the product. I can build the API, database, interface, and deployment around it, so what I ship works for real users rather than just in a notebook.
End-to-End Ownership
Architecture, evaluation, deployment, monitoring, and cost tracking — not just the model.
Evaluated, Not Assumed
Eval sets, regression tests, and validation gates catch failures before users do.
Agents with Guardrails
Approval gates and human review keep autonomous agents accountable without slowing them down.
Cost-Aware
Per-provider, per-model LLM usage tracking so spend stays visible and predictable.
Skills
Work
Certifications
Awards & Recognition
- Loading…
Publications
Contact
I'm currently open to new AI engineering, full-stack, and data projects. Whether you have a system to build, a pipeline to automate, or just want to talk through an idea — my inbox is open.
Say hello → addeyemi.99@gmail.com Download Résumé ↓