Founding AI Research Engineer - Robot Learning

About the role

The role involves expanding learned components of our multi-agent action expert architecture, ensuring the system remains production-safe. You will be responsible for the full lifecycle of these components, from data collection and model training to edge deployment on Jetson AGX Orin.

Responsibilities

• Train and deploy VLA models for contact-rich manipulation using our imitation learning infrastructure
• Build the data flywheel: develop teleoperation pipelines (GELLO, SpaceMouse, VR), DAgger-style online correction, and demonstrate curation
• Research and prototype world models for surface state prediction, spray dynamics, and anomaly detection
• Design offline evaluation metrics that predict real-world finishing quality before deployment
• Optimize models for edge: implement TensorRT compilation, latency profiling, and memory budgeting on dual Jetson AGX Orin
• Design the interface where learned policies propose actions and deterministic safety layers enforce constraints

Requirements

• BS/MS/PhD in CS, Robotics, ML, or equivalent experience shipping learned systems on physical robots
• Strong Python and PyTorch skills; comfortable modifying research codebases
• Experience in at least two of: imitation learning, RL, vision-language models, robot learning from demonstration, sim-to-real
• Track record deploying ML on real hardware: not just training to convergence, but debugging why the policy fails on the actual robot
• Experience with ROS2 or equivalent robotics middleware
• Experience working with Simulation Systems like Isaac Sim
• GPU profiling and optimization (TensorRT, ONNX, CUDA)
• Plus: hands-on with VLA architectures (π0/π0.5, OpenVLA, RT-2, Octo) or foundation model fine-tuning for robotics
• Teleoperation data collection and DAgger/HG-DAgger pipelines
• Experience with world model architectures (DreamerV3, V-JEPA, latent dynamics models)
• Background in Construction, manufacturing, or contact-rich industrial domains

Qualifications

• Publications at CoRL, RSS, ICRA, NeurIPS: valued but equivalent shipped work counts