About the Role
You will turn research into reliable models for physical robots. You will build training, evaluation, and inference systems using real-world embodied data, including video, lidar, audio, state-action logs, and reasoning traces. You will develop multimodal perception models, curate datasets, deploy containerized services, optimize models for embedded hardware, and monitor their field performance.
Requirements
•MS or PhD in machine learning, robotics, computer science, or a related field
•1+ years of industry or applied research experience training and shipping machine learning models
•Strong engineering fundamentals in Python, Go, and/or C++
•Fluency in PyTorch or JAX
•Hands-on experience with multimodal models, perception, or reinforcement and imitation learning
•Experience running models on edge hardware under latency and memory constraints
•Experience with TensorRT, ONNX, or other inference optimization toolchains
•Experience with ROS2 and Docker-based deployment on robots
•Experience building datasets or benchmarks used outside your own team
•Publications at CoRL, RSS, ICRA, NeurIPS, ICML, or ICLR
Responsibilities
•Build multimodal perception models for socially aware robots
•Build and scale pipelines that transform robot logs into curated and labeled datasets
•Ship models as containerized services in the OM1 deployment stack
•Own model latency, reliability, and field regressions
•Move models from prototypes to production on physical robots
•Integrate, fine-tune, and optimize foundation models for real-time perception and reasoning on embedded compute
Benefits
•Equity
