Staff AI Engineer, Coding Agents & Benchmarks

Neolife Updates; New York (NY); On-site; USD 270,000 - 350,000; Full time

Job summary

Handshake, based in New York, NY, is hiring a Member of Technical Staff, Coding Agents. You will help define benchmarks and evaluation data for frontier coding agents, partnering with top AI researchers and thousands of engineers to push the field forward.

You will publish benchmarks, shape the trajectory of the coding-agent landscape, and contribute open-source tools and research papers. This is a high-ownership role with influence on technical direction and open science in AI for software.

Qualifications

• Experience publishing benchmarks for AI/ML systems.
• Strong track record of OSS contributions and public code.
• Experience with evaluating AI systems and software agents.

Responsibilities

• Publish coding benchmarks that challenge state-of-the-art frontier agents.
• Shape understanding of where the coding-agent landscape is headed via public studies.
• Collaborate with leading AI labs to improve coding models.
• Contribute openly through benchmarks, open-source tools, research, and technical writing.

Skills

Coding benchmarks

Open-source contributions

Agent harnesses

Tools

GitHub

Job description

Handshake, based in New York, NY, is hiring a Member of Technical Staff, Coding Agents. You will help define benchmarks and evaluation data for frontier coding agents, partnering with top AI researchers and thousands of engineers to push the field forward.

You will publish benchmarks, shape the trajectory of the coding-agent landscape, and contribute open-source tools and research papers. This is a high-ownership role with influence on technical direction and open science in AI for software.