General Motors is seeking to research and develop state-of-the-art AI/ML approaches, especially Foundation Models, to tackle challenging problems in the areas of robot perception, whole-body motion planning/controls, spatial safety and autonomous manipulation to advance automation capabilities and ensure systems are at the forefront of the industry.
Requirements
- 3+ years of first-hand professional experience in Machine Learning and data driven approaches to visual perception and autonomy problems, with a good understanding of recent ML approaches such as LLMs & ViTs.
- Proficiency in Python or C++ with hands-on experience on Machine Learning frameworks (e.g. PyTorch) and model development, including training, tuning and optimization, for realistic applications.
- Familiarity with 3D computer vision and/or graphics pipelines.
- PhD in Computer Science, Machine Learning, Robotics, Computer Vision or a related research field.
- A track record of relevant publications (e.g. ICRA, IROS, NeurIPS, ICML, CVPR, ICCV, RSS, CoRL) or product deliverables.
- Hands-on robotics experience, such as autonomous vehicles (AV), ADAS, or industrial automation systems in manufacturing environments.
- Experience with robotics frameworks such as ROS/ROS2, (e.g., Nav2, MoveIt).
Responsibilities
- Drive independent research and prototyping initiatives in robotics foundation models and reinforcement learning models, focusing on breakthrough approaches in perception, and manipulation, for example open-vocabulary panoptic scene understanding, scaling up multi-modal LLMs, sim2real/real2sim techniques, end-to-end vision-language-action (VLA) models, efficient model inference, video tokenization
- Lead technical projects from conceptualization through implementation, enabling robust performance in real world applications
- Work with engineers to process and prepare training data, including data governance, provenance tracking, data quality checks and creating reusable data pipelines.
- Design and execute experiments to test model capabilities on the simulator and on the embodiment, validate performance across different scenarios, create a baseline and iteratively improve model performance.
- Work closely with R&D, engineers, and leaders across multiple teams, participate in knowledge sharing, support integration efforts with robotics hardware teams, and help document best practices and methodologies.
- Stay updated with emerging technologies and best practices in robotics and lead and participate academic/industrial collaborations.
- Contribute to the team's technical strategy and help shape our approach to next-generation robotics challenges.
Other
- Onsite - This position requires the employee to be onsite full time. The primary work location will be at the General Motors Global Technical Center in Warren, MI.
- MSc in Computer Science, Electrical Engineering, Robotics, or a related field.
- Passionate about robotics, with a strong desire to accelerate the application of robotics with AI.
- Generate intellectual property, document results and publish papers.
- Understanding of CI/CD pipelines and modern software development practices.
