Member of Technical Staff, Coding Agents
Core
Define how frontier coding agents are benchmarked and improved by developing new benchmarks, reward and verifier systems, agent-evaluation methodologies, and data-quality techniques.
Role type
Senior IC research engineer (coding agents)
Builds
Benchmarks, reward and verifier systems, agent-evaluation methodologies, data-quality techniques, open-source software, and research products
Domain
AI for Coding / Frontier AI
Deliverable
production ML models
Required skills
Coding benchmark creation, agent-evaluation methodology design, data-quality techniques, open-source tool development, technical writing, research publication, software engineering, agent harness knowledge
Preferred skills
Experience with frontier coding agents, deep knowledge of agent harnesses
Technologies
Coding agents, agent harnesses
Responsibilities
Create/publish Coding benchmarks that challenge state-of-the-art frontier agents, Understand/shape the frontier of coding agents and where the space is headed, Help the world's top AI Labs improve their models for coding, Publicly contribute to the field through benchmarks, open-source tools, research, and technical writing
Seniority
Senior, hands-on IC
