Applied Robotics Engineer

san francisco, cafull time$150K-$280Kgenerous equity

Connect reliable LLM agents with working robot behavior, bringing EQ's research into human interaction into physical systems. Build agents that turn task descriptions into robot policies, improve them through simulation and execution feedback, and deploy tested behavior to robots and customer-facing services.

Work across perception, language, social context, and action using video, depth, IMU, trajectory, and interaction data.

what you'll own

  • Design model-facing tools and APIs, multi-step agent loops, and reusable skill libraries for robot tasks.
  • Train and post-train robot policies using demonstrations, imitation learning, reinforcement learning, and related robot-learning methods.
  • Generate and test policies in simulation, using execution feedback, context management, and retry budgets to recover from failures.
  • Build reproducible evaluations, held-out tasks, and regression tests that verify success independently of model self-reports. Evaluate task success, timing, clarification, recovery, and safe abstention.
  • Deploy tested policies to physical robots and diagnose failures across policies, sensors, calibration, and hardware.
  • Serve concurrent agents on GPU-backed services with queues, retries, cancellation, cost controls, and isolated execution of generated code. Track latency, reliability, and compute cost.

what we're looking for

  • Strong Python and experience building LLM agents that run unattended over multiple steps.
  • Demonstrated experience deploying and debugging manipulation, imitation-learning, or control policies on physical robots, with measurable results.
  • Strong robotics fundamentals, including kinematics, coordinate frames, feedback control, calibration, and actuator limits; experience with ROS 2 or equivalent.
  • Experience with Isaac Sim/Lab, MuJoCo, SAPIEN, or equivalent, including contact dynamics and sim-to-real discrepancies.
  • PyTorch or JAX and practical experience operating GPU-backed services, with care for sandboxing, network restrictions, resource limits, failure recovery, and production reliability.

Research in agents, program synthesis, or robot learning is useful, as are LeRobot, multi-agent orchestration, on-device inference, power profiling, fleet deployment, and OTA updates.