Torc Robotics
Senior, Machine Learning Engineer - 3D Perception
$177K–$213K
Remote, U.S, Ann Arbor, MI, Fort Worth, TX, Blacksburg, VA +1 · Remote · Senior · Full-time · Posted Jul 21, 2026
- Location
- Remote, U.S, Ann Arbor, MI, Fort Worth, TX, Blacksburg, VA
Ann Arbor, Michigan, United States - Experience
- Bachelor’s degree with 6+ years of industry experience, OR Master’s degree with 3+ years, OR Ph.D. with 1+ years.
- Education
- Bachelor’s degree in Computer Science, Robotics, Electrical Engineering, Machine Learning, or a related technical field; alternatively, a Master’s degree or Ph.D. as specified.
About the job
Develop and deploy production machine learning models for Torc’s autonomous-truck perception systems, with a focus on Bird’s Eye View perception and multimodal sensor data.
What you'll do
- Own end-to-end model development, from data preparation and training through evaluation and deployment.
- Analyze model performance and failure modes, then improve model robustness, accuracy, and generalization.
- Integrate perception models into production autonomy software and mentor junior engineers.
What they ask for
- Production machine learning experience in computer vision, perception, robotics, or autonomous systems.
- Strong Python and PyTorch skills, including production-quality ML code.
- Experience training, evaluating, and improving deep learning models using large-scale datasets.
- Experience with image-based and/or 3D perception systems and debugging model performance.
Nice to have
- Experience with autonomous driving or robotics perception, LiDAR, point clouds, sensor fusion, or other 3D perception techniques.
- Experience with temporal perception, C++, ROS, production deployment, distributed training, or perception evaluation.
Pay
$177,300 — $212,800 USD (base salary)
Tools
Python, PyTorch, LiDAR, C++, ROS
AI focus
Develop production ML for autonomous-truck perception, especially Bird’s Eye View, camera-based and 3D perception, and multimodal sensor understanding.
Model-written summary · the original posting is authoritative