DeveloperJobs.io
← Back to all jobs
Pantograph

Robotics Machine Learning Engineer

San Francisco, CA $150k - $260k/yr Full time Posted 7h ago

Job Description

Build real robots from capable AI models. Pantograph is hiring a Robotics Machine Learning Engineer in San Francisco, CA (onsite) to connect models to robot observations and actions, develop tools and controllers, and validate performance through evaluations in both simulation and on the fleet.

You will focus on turning AI research into systems that operate reliably in the real world, with a workflow grounded in deploying, measuring, and improving based on experience from real hardware. Compensation for this role is USD 150,000 - 260,000 per year.

What you’ll do

  • Design and build systems that convert capable AI models into robots that perform useful real-world work.
  • Connect models to robot observations and actions so decisions translate into control.
  • Build the tools, skills, and controllers models rely on to complete tasks.
  • Develop evaluations in simulation and on the fleet.
  • Determine the right orchestration strategy: 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 tradeoffs across capability, reliability, latency, safety, and how easily the system can be understood and supervised, guided by real deployments.
  • Collaborate closely with research, robot software, and product teams to maintain a tight loop between experiments and real-world results.
  • Diagnose failures and identify where the fix belongs, including observation quality, tool selection, orchestration changes, policy or controller updates, or other system improvements.

What you’ll need

  • Deep experience in robotics, including control, perception, planning, and learned policies, with evidence of making robots succeed on real hardware.
  • Strong simulation skills: use simulation to develop and test systems, and understand where it diverges from reality.
  • Experience designing and shipping robotic or AI systems that people use, with clear proof of what improved outcomes.
  • Excellent experimental design and interpretation: separate competing explanations, identify confounders, and judge what evidence does and does not support.
  • Intuitive understanding of model behavior: what models understand, what confuses them, and how behavior shifts with tools, context, and feedback.
  • Enjoyment of failure analysis, with curiosity about how systems behave beyond aggregate metrics.
  • Pragmatism about methods, emphasizing performance on real tasks over novelty or added complexity.
  • Ability to build reliable software end-to-end, 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 experience

  • 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

$150K - $260K

Similar Jobs