Machine Learning Engineer Robot Learning Loco Manipulation
Path RoboticsVisit Path Robotics website
Path Robotics develops physical-AI robotic welding systems for manufacturing.
Columbus, United States
Funding history
About Path Robotics
Path Robotics builds autonomous welding cells and mobile welding systems powered by its Obsidian AI model, which uses real-time sensing and adaptation to weld variable industrial parts.
Skills
Action ChunkingBehavioral CloningData PipelineData VersioningDiffusion ModelExperiment TrackingFlow MatchingIsaac LabIsaac SimLocomotionMachine LearningManipulationMujocoOnnxPythonPytorchQuantizationReinforcement LearningRoboticsRobot LearningSim-To-Real TransferSimulationTensorrtTraining InfrastructureWhole-Body Control
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will build robot-learning infrastructure, data pipelines, simulation environments, model architectures, and deployment workflows. You will train manipulation, locomotion, and whole-body control policies, deploy them through phased rollouts, and improve models using real-world execution data.
Requirements
- Ph.D. or Master’s degree in Robotics, Mechanical Engineering, Electrical Engineering, Computer Science, or a related field, or equivalent experience
- 2+ years of hands-on robot learning experience
- Experience training policies and deploying them on real robot hardware
- Sim-to-real transfer experience
- Experience implementing diffusion-based or flow-matching robot action policies and action chunking
- Experience applying reinforcement learning for robotics on real hardware
- Strong Python, PyTorch, and production ML training infrastructure skills
- Practical experience with NVIDIA Isaac Sim, Isaac Lab, MuJoCo, or equivalent
- Experience debugging, iterating on, and deploying physical robots
- Strong communication skills
Responsibilities
- Build robot-learning infrastructure, data pipelines, simulation environments, model architectures, and deployment workflows
- Establish training pipelines, experiment tracking, data versioning, and reproducible sim-to-real workflows
- Train policies for manipulation, locomotion, and whole-body control
- Deploy models through phased rollouts and use execution data for continuous improvement
- Collaborate with mechanical, perception, robotics, and manufacturing specialists
- Participate in within-department rotation across home teams
Benefits
- Daily free lunch
- Flexible PTO
- Medical, dental, and vision coverage
- 6 weeks of fully paid parental leave plus an additional 6–8 weeks for birthing parents
- 401(k) retirement plan through Empower
- Employee referral bonuses