Staff Engineer, Coding Agents Benchmarking

Handshake; Mountain View (CA); Presencial; USD 180.000 - 240.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Health Insurance

Fertility and family forming

LGTBQ+ coverage

Mental health

Tax savings

Life & disability insurance

401k match

Equity

Financial management

Learning & development

Community leader support

Parental leave

Flexible time off

Sabbatical

Volunteer time off

Descripción de la vacante

Handshake is seeking a Member of Technical Staff to help define how frontier coding agents are benchmarked and improved. You will partner with world-class AI researchers and thousands of software engineers to develop benchmarks, reward and verifier systems, agent-evaluation methodologies, and data-quality techniques for AI-powered coding.

Early team members will influence technical direction and open-source projects.

Formación

• Extremely passionate about building software with agents and tinkering with coding agents.
• Published research on AI for Software/Code-Generation at NeurIPS, ICLR, ICML, COLM, etc.
• Extensive software engineering experience or strong GitHub OSS contributions with deep knowledge of agent harnesses.
• Comfort operating in an ambiguous, fast-moving environment with substantial ownership.
• Previous experience working on a Coding benchmark.

Responsabilidades

• Create/publish Coding benchmarks that challenge state-of-the-art frontier agents.
• Understand/shape the frontier of coding agents and publish studies of findings.
• Help leading AI labs improve their models for coding.
• Contribute to the field through benchmarks, open-source tools, research, and technical writing.

Descripción del empleo

Handshake is seeking a Member of Technical Staff to help define how frontier coding agents are benchmarked and improved. You will partner with world-class AI researchers and thousands of software engineers to develop benchmarks, reward and verifier systems, agent-evaluation methodologies, and data-quality techniques for AI-powered coding.

Early team members will influence technical direction and open-source projects.