Built from work this engineer published themselves. It makes no claim that they are available for hire, and it is marked noindex until they claim it. Source: hamel.dev. This is you, or it should not be here? Write to hello@aiengineer.me.
ai-engineer
Hamel Husain
Independent ML consultant; the field notes on LLM evaluation.
Independent machine-learning consultant whose public writing on evaluation — error analysis first, LLM-as-judge used carefully, a bespoke eval harness before any framework — is widely cited as a reference for teams shipping LLM features. Previously built developer-facing ML tooling at GitHub, including work on CodeSearchNet.
Technical stack & depth
Evaluation
Evals, traces, and a quality bar that is not a vibe check.
Fine-tuning
Data pipelines, adapters, and knowing when training is the wrong move.
Production hardening
Latency, cost, observability, and the path from a notebook to a service.
Engineered solutions
- Write-upYour AI product needs evalshamel.dev
Widely referenced write-up on building an evaluation system for an LLM product.
- Portfoliogithub.com/hamelsmugithub.com
Open-source ML tooling and notebooks, including earlier developer-tooling work from GitHub.
Something here out of date or wrong? Write to hello@aiengineer.me and it will be corrected or removed.