Founding AI Research Engineer - Robot Learning

About OriginOrigin is building Physical AI for the built world - starting with autonomous robots for Interior Construction. We are building Construction Action Models which allows our modular robots to learn, adapt and work in unstructured construction job site.Our robots are already deployed on live sites in New York City, helping accelerate schedules for large-scale commercial projects while improving safety and predictability on the job site. Backed by Tier-1 investors, Origin is working to close the gap between America's surging demand for housing, data centers, and manufacturing infrastructure, and the construction industry's growing labor shortage.The RoleOur system runs a Multi Agent Action Expert architecture: classical precision algorithms orchestrated alongside learned policies. The job is systematically expanding the learned components while keeping the system production-safe. You own the full lifecycle of learned components on OG-1: from data collection and model training through edge deployment on Jetson AGX Orin. Every research project will have a deployment milestone. This is not a lab position.What You Will DoTrain and deploy VLA models for contact-rich manipulation using our imitation learning infrastructureBuild the data flywheel: teleoperation pipelines (GELLO, SpaceMouse, VR), DAgger-style online correction, demonstration curationResearch and prototype world models for surface state prediction, spray dynamics, and anomaly detectionDesign offline evaluation metrics that predict real-world finishing quality before deploymentOptimize models for edge: TensorRT compilation, latency profiling, memory budgeting on dual Jetson AGX OrinDesign the interface where learned policies propose actions and deterministic safety layers enforce constraintsRequirementsBS/MS/PhD in CS, Robotics, ML, or equivalent experience shipping learned systems on physical robotsStrong Python and PyTorch; comfort modifying research codebases (you'll work directly with open-source VLA implementations)Experience in at least two of: imitation learning, RL, vision-language models, robot learning from demonstration, sim-to-realTrack record deploying ML on real hardware: not just training to convergence, but debugging why the policy fails on the actual robotWorking knowledge of ROS2 or equivalent robotics middlewareExperience working with Simulation Systems like Isaac Sim. GPU profiling and optimization (TensorRT, ONNX, CUDA); you understand why 200ms policy latency kills contact controlStrong PlusHands-on with VLA architectures (π0/π0.5, OpenVLA, RT-2, Octo) or foundation model fine-tuning for roboticsTeleoperation data collection and DAgger/HG-DAgger pipelinesWorld model architectures (DreamerV3, V-JEPA, latent dynamics models)Construction, manufacturing, or contact-rich industrial domainsPublications at CoRL, RSS, ICRA, NeurIPS: valued but equivalent shipped work counts