Staff, Machine Learning Engineer - BEV/Multi-Modal Perception
Torc Robotics2 months ago
Base Salary
$216k - $259k/yr
Responsibilities
- Lead the technical roadmap and development of BEV perception models for detection, segmentation, road topology, and scene understanding.
- Design architectures that fuse camera, LiDAR, radar, and HD map data into unified spatial representations.
- Develop foundational perception models using BEV transformers, voxel-based encoders, and implicit scene representations.
- Own large-scale training workflows, including data sampling, augmentation, distributed training, and hyperparameter optimization.
- Improve model robustness and generalization for low visibility, occlusions, rare scenes, and cross-domain conditions.
- Establish evaluation frameworks for geometric accuracy, temporal stability, and cross-domain transfer performance.
- Collaborate with sensor calibration, mapping, and fusion teams on cohesive perception model interfaces.
- Mentor ML engineers and promote strong practices in experimentation, code quality, and model validation.
- Explore self-supervised learning, large-scale pretraining, and foundation models for 3D perception.
Requirements
- 10+ years of experience in deep learning for perception, 3D vision, and/or autonomous systems.
- M.S. or Ph.D. in Computer Science, Electrical Engineering, Robotics, or a related field, or equivalent practical experience.
- Proven expertise in BEV modeling, 3D scene understanding, and multi-view fusion.
- Strong experience with multi-modal sensor fusion, particularly camera and LiDAR integration.
- Proficiency in Python and deep learning frameworks such as PyTorch or TensorFlow.
- Experience with large-scale data pipelines, distributed training, and experiment management systems.
- Demonstrated technical leadership in ML model innovation and mentoring.
- Experience with autonomous driving or robotics perception in production environments is preferred.
- Experience with MLOps and Ray is preferred.
- Familiarity with 3D labeling, calibration, sensor simulation pipelines, and deployment tradeoffs is preferred.
- Publications or open-source contributions in venues such as CVPR, ICCV, NeurIPS, ICRA, or CoRL are a plus.
Benefits
- Competitive compensation package with bonus and stock options.
- 100% employer-paid medical, dental, and vision premiums for full-time employees.
- 401(k) plan with a 6% employer match.
- Flexible scheduling, generous paid vacation available immediately after start date, and company-wide holiday office closures.
- AD&D and life insurance.
- Hybrid work in Ann Arbor, Michigan or remote work within the United States.
- Full-time position.
Categories
ML EngineeringRobotics
About Torc Robotics
Torc Robotics develops autonomous driving software for heavy-duty trucks, offering a full self-driving stack, mapping, and perception for freight carriers and OEMs. Founded in 2005 and headquartered in Blacksburg, Virginia, it was acquired by Daimler Truck in 2019. As a subsidiary, Torc focuses on commercializing Level 4 trucking with its parent’s vehicle platforms and industry partnerships in North American freight transport.