Member of Technical Staff (Software Engineer, Enterprise Agent Evals & Efficiency)

Highlights

• Build realistic enterprise eval environments to test agents on real workflows.
• Own the eval-to-ship loop improving task success, latency and cost.
• Improve agent tools, skills and routing to automate complex enterprise work.

What they offer

• Equity

Ideal candidate

Systems-minded engineer who loves measurement and iteration, thriving in ambiguity and owning production systems end-to-end to make enterprise agents faster, cheaper and more reliable.

Requirements

• 5+ years of software engineering or ML engineering owning complex production systems end-to-end
• Strong system design for reliable, scalable experimentation, evaluation or data-intensive infrastructure
• Strong proficiency in Python, Go, or Rust with ability to work across multi-language stack
• Hands-on experience building, evaluating or improving LLM apps or agents with tool use and multi-step workflows
• Deep expertise in eval infrastructure and grading, agent harnesses and skills, simulations, or model routing and efficiency
• Strong experimental and statistical judgment defining success criteria and diagnosing failures
• Track record leading ambiguous cross-team initiatives and raising quality through mentorship