Software Engineer

GW227
  • $200,000-$300,000
  • San Francisco, CA
  • Permanent

About the job


Agent Systems Engineer - San Francisco or Redwood City


A company who are building AI systems with general physical ability are looking for a Senior Agent Systems Engineer to design and implement the planning, orchestration and tool-use behaviors that allow AI Agents to operate complex physical and experimental workflows.


What Will I Be Doing:


  • Build agent planners, tool-call flows, and state machines using LangGraph or similar frameworks.
  • Design schemas, action adapters, and cross-tool interfaces enabling deterministic, traceable LLM tool use.
  • Develop error handling, timeout strategies, retries, rollbacks, and replay mechanisms for robust agent behavior.
  • Collaborate with systems architecture, infrastructure, and ML teams to integrate agents into real engineering toolchains.


What We're Looking For:


  • Strong experience building agent systems, LLM tool-calling pipelines, or structured orchestration frameworks.
  • Deep understanding of schemas, action abstractions, reproducibility, and deterministic multi-step execution.
  • Ability to reason about system-level failure modes, edge cases, and safe tool interaction.
  • Comfortable working across AI, systems, and domain-tooling interfaces in a fast-moving, high-precision environment.
  • Above all, we’re looking for candidates who demonstrate world-class excellence.


What’s in It for Me


  • $200k - $300k dependent on experience and meaningful equity
  • The chance to build foundational agentic infrastructure for physical AI
  • Ownership of end-to-end, real-world systems that directly drive scientific breakthroughs
  • A role at the core of a rapidly growing, deeply technical team
  • The opportunity to define how AI interacts with the physical world


Apply now for immediate consideration!


Kirstie Moffat ML Research & Engineering Recruiter

Apply for this role