- ML engineer and independent consultant, Parlance Labs1
Hamel Husain is a machine learning engineer and independent consultant at Parlance Labs who helps teams debug, analyze, and measure their AI systems, work Husain calls evals, and co-teaches a course on AI evals for engineers and product managers. Husain previously did applied machine learning at GitHub and Airbnb; Husain's homepage links early LLM research from that time, the CodeSearchNet Challenge paper (2019), of which Husain is first author. At GitHub, Husain also wrote the 2020 GitHub blog post introducing nbdev, a literate programming environment for Python that GitHub helped fast.ai develop. Husain is a co-author, with Eugene Yan, Shreya Shankar, and others, of "What We've Learned From A Year of Building with LLMs" (2024).12345
At a glance
- Current role
- ML engineer and independent consultant
- Company
- Parlance Labs
- Sector
- Independent
- Work listed
- 3
- Sources cited
- 11
- Profile reviewed
Career
Hamel Husain did applied machine learning at Airbnb and at GitHub, where Husain's homepage says early LLM research on code understanding was carried out; Husain is first author of the 2019 CodeSearchNet Challenge paper from that period. Husain now works as a machine learning engineer and independent consultant at Parlance Labs, helping teams build AI products.213
Teaching and writing
Husain's writing focuses on what Husain calls evals: debugging, analyzing and measuring AI systems. Long-form posts on Husain's blog include "Your AI Product Needs Evals" (March 2024), a guide to using LLM-as-a-judge validated against human labels (October 2024), and "A Field Guide to Rapidly Improving AI Products" (March 2025).2678
With Shreya Shankar, Husain co-teaches the Maven course AI Evals for Engineers and PMs. In July 2024 Husain released Mastering LLMs, a free survey course of workshops and talks by practitioners on evals, retrieval-augmented generation, fine-tuning and prompt engineering. Husain also co-wrote the 2024 essay "What We've Learned From A Year of Building with LLMs".9105
Open-source work
While at GitHub, Husain wrote the November 2020 GitHub blog post introducing nbdev, a literate programming environment built on Jupyter notebooks that GitHub helped fast.ai develop; nbdev is published under the Apache 2.0 license. Husain's blog later includes a January 2026 post on why Husain stopped using nbdev.4112
Work and contributions
CodeSearchNet Challenge Open data
First author of "CodeSearchNet Challenge: Evaluating the State of Semantic Code Search" (2019), which released the CodeSearchNet Corpus of functions from open-source code in Go, Java, JavaScript, PHP, Python, and Ruby, with expert relevance annotations for evaluating code search.32
nbdev Open-source code
Wrote GitHub's 2020 blog post introducing nbdev, a literate programming environment built on Jupyter notebooks that GitHub assisted fast.ai in developing, with documentation generation and continuous integration through GitHub Actions. The repository is licensed under Apache 2.0.411
What We've Learned From A Year of Building with LLMs Published research
Co-author of the 2024 essay on lessons from building LLM products, published on applied-llms.org and by O'Reilly in three parts.5
Timeline
- Posted the CodeSearchNet Challenge paper on evaluating semantic code search as first author.3
- Introduced nbdev on the GitHub blog.4
- Published "Your AI Product Needs Evals" on constructing domain-specific LLM evaluation systems.6
- Co-authored "What We've Learned From A Year of Building with LLMs".5
- Released Mastering LLMs, a free survey course of practitioner talks on LLMs.10
- Published a guide to building and validating LLM-as-a-judge evaluators.7
- Published "A Field Guide to Rapidly Improving AI Products".8
Other documented roles
Roles the sources document that are not confirmed as current.
Where they work
- Parlance Labs 1 person in the wiki
Related people
- Scott TolinskiTeaching and writing · Developer tools
- ThePrimeagenTeaching and writing · Developer tools
- Alessio FanelliTeaching and writing · Developer tools
- argoTeaching and writing · Developer tools
- AI ExplainedTeaching and writing · Evaluation and benchmarks
- Kilian LieretEvaluation and benchmarks · Developer tools
- Ben DavisTeaching and writing · Developer tools
- Nate RushEvaluation and benchmarks · Developer tools
- Kristian FagerlieTeaching and writing · Developer tools
- Shawn LewisDeveloper tools · Evaluation and benchmarks
Suggest a correction or removal
Profiles cover public professional work only, and each statement cites a source. If something is out of date, missing or wrong, tell us and link a source. People can also ask for their profile to be corrected or removed.
References
11 sources · profile reviewed Oct 21, 2026 · data updated Oct 21, 2026
- hamelsmu (Hamel Husain) on GitHub (profile and README)
- Hamel Husain's Blog — homepage
- CodeSearchNet Challenge: Evaluating the State of Semantic Code Search (arXiv 1909.09436)
- Nbdev: A literate programming environment that democratizes software engineering best practices (GitHub Blog)
- What We've Learned From A Year of Building with LLMs — Applied LLMs
- Your AI Product Needs Evals — Hamel's Blog
- Using LLM-as-a-Judge For Evaluation: A Complete Guide — Hamel's Blog
- A Field Guide to Rapidly Improving AI Products — Hamel's Blog
- AI Evals For Engineers & PMs by Hamel Husain and Shreya Shankar (Maven)
- An Open Course on LLMs, Led by Practitioners — Hamel's Blog
- AnswerDotAI/nbdev LICENSE (Apache-2.0)