You will help define how frontier coding agents are benchmarked and improved.
You will partner with the world's top AI researchers and thousands of software engineers.

What You'll Do:

Create and publish coding benchmarks that challenge state-of-the-art frontier agents.
Study and shape the frontier of coding agents, publishing impactful findings.
Help top AI labs improve their models for coding.

What We're Looking For:

Extreme passion for building software with agents and tinkering with the latest coding agents.
Comfort operating in an ambiguous, fast-moving environment with substantial ownership.
Demonstrated experience with coding benchmarks, published research, or a strong software engineering background.

Perks:

Work at the very frontier of AI with major AI labs.
Publish results through open-source benchmarks, papers, and blogs.
Help build an early technical organization shaping the roadmap and culture.

Handshake

Handshake's mission is to organize expert human knowledge to advance the AI economy, working directly with frontier labs on data, evaluations, and post-training challenges. It is a rapidly growing startup with a small, high-ownership technical team from top AI companies.

Apply for This Position