ML Engineer I, Robotics

What we’re doing isn’t easy, but nothing worth doing ever is. 

We envision a future powered by robots that work seamlessly with human teams. We build artificial intelligence that enables service robots to collaborate with people and adapt to dynamic human environments. Join our mission-driven team as we build out current and future generations of robots.

As an ML Engineer I, you will support development of ML models and infrastructure by building datasets, running experiments, and improving evaluation tooling. You’ll work closely with senior engineers to help ship reliable autonomy improvements. Your work will directly impact iteration speed, model quality, and the team’s ability to measure progress on real robot behavior.

• Build and maintain datasets: episode extraction, data validation, train/val/test splits, and dataset versioning.
• Run training experiments and ablations; track results and maintain reproducible configs.
• Improve evaluation pipelines: offline replay tests, metrics dashboards, failure case triage tools.
• Support labeling workflows: sampling strategy, QA feedback loops, and integration of model-assisted labels.
• Assist with model export and benchmarking tasks (latency, memory, throughput) on target hardware.
• Participate in on-robot testing and help diagnose performance gaps with logs and visualizations.
• Collaborate with cross-functional partners (AI platform, cloud infra, ops) to close the loop from field data to model improvements.

• Bachelor’s or Master’s degree in Robotics, Computer Science, Electrical Engineering, or related field (PhD a plus).
• 0–2 years of experience (or strong project/research experience) in ML, CV, robotics, or software engineering.
• Proficiency in Python and familiarity with PyTorch or another deep learning framework.
• Experience with data processing pipelines and experiment tracking.
• Ability to communicate clearly and work effectively with a team.

• Coursework or project experience in robotics perception, navigation, manipulation, or ML systems.
• Familiarity with ROS, common sensor modalities, and logging/replay workflows.
• Experience with annotation tools and dataset QA processes.
• Experience using cloud tooling for training jobs (AWS/GCP) and distributed training concepts.