Frontier AI Coding Benchmarks Engineer

Handshake; United States; Remote; USD 150,000 - 190,000; Full time

Job summary

Handshake is building the next generation of AI tooling to advance the AI economy. We are hiring a strategist who will define benchmarks for frontier coding agents and publish findings in open venues.

You will partner with leading AI researchers and thousands of software engineers, shaping the roadmap and owning benchmarks that push state-of-the-art. This role offers high ownership in a rapidly growing startup.

Qualifications

• Experience with coding benchmarks and evaluating AI agents.
• Track record of published research or strong software development background.
• Ability to publish results through open benchmarks and papers.

Responsibilities

• Create and publish coding benchmarks that challenge frontier agents.
• Study frontier coding agents and publish impactful findings.
• Support labs in improving models for coding.

Skills

Software engineering

AI benchmarks

Open-source publications

Job description

Handshake is building the next generation of AI tooling to advance the AI economy. We are hiring a strategist who will define benchmarks for frontier coding agents and publish findings in open venues.

You will partner with leading AI researchers and thousands of software engineers, shaping the roadmap and owning benchmarks that push state-of-the-art. This role offers high ownership in a rapidly growing startup.