Machine Learning Engineer, Robot Learning, Loco-Manipulation
Path Robotics5 months ago
Columbus, OH, USAMid Level
H1B sponsor
Responsibilities
- Build the robot-learning stack from the ground up, including training infrastructure, data pipelines, simulation environments, model architectures, and deployment workflows
- Develop multimodal perception, scene-understanding, and learned-action-generation systems
- Train policies for manipulation, locomotion, and whole-body control coupling using behavioral cloning, diffusion or flow-matching action generation, and reinforcement-learning fine-tuning
- Establish ML infrastructure for training pipelines, experiment tracking, data versioning, and reproducible sim-to-real workflows
- Deploy robot-learning systems through phased production rollouts and use real-world execution data for continuous improvement
- Collaborate with mechanical, perception, and robotics engineers and manufacturing experts
- Participate in within-department rotation across home teams
Requirements
- Master’s or Ph.D. in Robotics, Mechanical Engineering, Electrical Engineering, Computer Science, or a related field, or equivalent experience
- At least 2 years of hands-on robot-learning experience training and deploying policies on real robot hardware
- Experience with sim-to-real transfer, simulation environments, domain randomization, and physical-robot debugging
- Implementation experience with diffusion-based or flow-matching robot action policies and action chunking
- Experience applying reinforcement learning to robotics on real hardware
- Strong Python programming skills and production-level experience with PyTorch and ML training infrastructure
- Practical experience with NVIDIA Isaac Sim, Isaac Lab, MuJoCo, or an equivalent platform
- Strong communication skills
- Preferred: edge inference using TensorRT, ONNX, FP16, or INT8 quantization
- Preferred: visual self-supervised representation learning for robotics or 3D vision
- Preferred: legged robotics or whole-body control experience
- Preferred: physics-informed machine learning and experience building ML pipelines or infrastructure
Benefits
- Daily free lunch
- Flexible paid time off
- 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
Categories
ML EngineeringRobotics
About Path Robotics
Path Robotics builds AI-driven robotic welding systems that autonomously plan and execute welds for metal fabrication and industrial manufacturers. The privately held company, founded in 2014 and headquartered in Columbus, Ohio, sells turnkey welding cells and software with support services, and is expanding into naval and defense fabrication compliant with NAVSEA codes.