Internal Acceleration, Research Engineer (Production)

Our Internal Acceleration team’s mandate is to build agents to accelerate the production of frontier tokens.

You’ll work directly with our founders and embed with our production team to build new agentic harnesses and operating systems to transform the way hardware is built in an AI native world. You’ll work on harnesses, tool use, context, and memory, execution environments, and evals that let agents conduct long-running engineering work that is useful.

This role is for engineers who thrive on ambiguity, have real product sense, and want to own problems end to end. It’s a whiteboard for future founders. The problems we solve are time-sensitive and business-critical. This role will not be a 9-5, and the ideal candidate is excited about that.

YOU MAY BE A GOOD FIT IF YOU

• Have at least 1-5+ years of experience building and shipping software end to end, ideally at a fast-moving startup
• Have built agents for complex, multi-step tasks that people depend on, beyond calling an API: tool design, long-context management, evals, and failure analysis.
• Are a strong software engineer who has built reliable systems others depend on, such as distributed systems, experiment infrastructure, or developer tooling.
• Use coding agents heavily, read their transcripts closely, and change the system when an agent is confidently wrong.
• Have high agency in unfamiliar domains. You find the real problem and drive it forward.
• Have product sense, design taste, and extreme attention to detail

KEY RESPONSIBILITIES

…