Robotics Engineer

We are seeking a Senior Robotics Data Engineer to join the Autonomous Robotics Center (ARC) Advanced Development team. This role is foundational to GM’s large-scale robotics initiative, enabling generalized and scalable AI perception and grasping solutions across thousands of manufacturing parts. You will architect and work on end-to-end robotic data systems, spanning real-world capture, simulation-generated data, annotation, curation, and lifecycle management.

Your work will directly power perception, grasping, and manipulation AI models, enabling rapid scaling across diverse part geometries and manufacturing contexts.

• Design and implement scalable data pipelines for large-scale robotic datasets (vision, depth, tactile, force/torque).
• Build infrastructure to support high-throughput data capture from real robots and simulation environments.
• Develop and deploy semi-supervised / self-supervised data labeling workflows to reduce manual annotation cost.
• Enable simulation-to-real (Sim2
  
  Real) data workflows, including domain randomization and synthetic data generation.
• Own data versioning, metadata, and dataset governance to support model training, evaluation, and regression testing.
• Partner closely with Robotics Perception, Grasping AI, and Simulation teams to define data requirements and KPIs.
• Establish data quality metrics that directly correlate with perception and grasping performance.

• 3+ years of experience in data engineering, machine learning systems, robotics, or related fields.
• Master’s degree in Engineering, Computer Science, Data Science, or equivalent practical experience.
• Strong hands-on experience with Python-based data tooling.
• Experience working with large, complex, multimodal datasets.
• Systems thinking mindset with strong cross-functional collaboration skills.

• Direct experience supporting robotics perception, grasping, or manipulation AI.
• Familiarity with robotics simulation platforms such as Isaac Sim and synthetic data generation.
• Experience with data labeling tools and annotation workflows at scale.
• Hands-on knowledge of Tensor Flow and/or PyTorch from a data systems perspective.
• Experience with Microsoft data ecosystems (e.g., Power BI, Azure data services).
• Exposure to self-supervised or weakly supervised learning techniques.