DataJobs.io
← Back to all jobs
Pantograph

Robotics Machine Learning Engineer

San Francisco, CA $150k - $260k/yr Full time Posted 4h ago

Job Description

Pantograph is building robots that translate capable AI into real-world usefulness. As a Robotics Machine Learning Engineer based in San Francisco, CA (onsite), you will connect models to robot observations and actions, develop the tools and controllers those models depend on, and create evaluation methods that work both in simulation and on the fleet.

In this role, you will work in a tight loop with research, robot software, and product teams. The focus is practical: use what you learn from real hardware deployments to guide decisions around capability, reliability, latency, safety, and how to supervise the system effectively.

Responsibilities

  • Design and build end-to-end systems that turn capable AI models into robots that perform useful tasks in the real world.
  • Connect models to robot observations and robot actions.
  • Build the tools, skills, and controllers the models rely on.
  • Develop and run evaluations in both simulation and on the fleet.
  • Determine the right level of autonomy, including when a frontier model should act directly, when it should coordinate faster learned policies or classical controllers, and when it should write its own tools or control code.
  • Make informed tradeoffs across capability, reliability, latency, safety, and understandability, using real deployments to ground your choices.
  • Diagnose system behavior and failures to identify what needs improvement, such as observations, tools, orchestration, policies or controllers, or other parts of the system.
  • Collaborate closely across teams, iterating from experiments to experience on real hardware.

Requirements

  • Deep experience in robotics including control, perception, planning, and learned policies, with experience getting robots to do useful work on real hardware.
  • Proficiency using simulation to develop and test systems, and strong judgment about where simulation diverges from reality.
  • Demonstrated experience designing and shipping robotic or AI systems that people use, with evidence of what made the solution better.
  • Strong experimental skills: designing experiments, interpreting results, separating competing explanations, identifying confounders, and understanding what evidence does and does not establish.
  • Intuition for model behavior, including what models understand, what confuses them, and how behavior shifts with tools, context, and feedback.
  • Enjoyment in investigating failures and understanding behavior beyond aggregate metrics.
  • Pragmatism: care more about performance on real tasks than the newest or most complex approaches.
  • Ability to build reliable software across the stack, from model APIs and inference to robot software and testing infrastructure.
  • Clear communication and comfort working across research and engineering.
  • Ability to use AI tools extremely effectively.

Bonus (If You’ve Worked With)

  • Agent harnesses, tool use, memory, or long-horizon tasks
  • Systems where models write and execute code or develop their own tools
  • Fine-tuning vision-language-action models or other large robot policies
  • Teleoperation, robot data collection, or learning from fleet data
  • Evaluation design, failure analysis, or safety testing
  • Inference optimization, including latency, throughput, and cost

Compensation

$150,000 - $260,000 per year

Similar Jobs