Torc Robotics, Inc.
Sr Machine Learning Engineer - ML Active Sensor & Camera Models
Torc Robotics, Inc., Ann Arbor, Michigan, us, 48113
Overview
Torc is a leader in autonomous driving, focused on developing software for automated trucks to transform how the world moves freight. Torc has a long history in autonomous vehicle technology and is part of the Daimler family. What you’ll do
Develop and optimize computer vision, LiDAR and radar-based ML models, including monocular and stereo depth estimation algorithms. Understand objects, lanes, obstacles, and weather conditions within the driving environment. Enhance perception systems to process multi-modal sensor data effectively. Use data science techniques to analyze model performance, data distributions, and identify corner cases. Contribute to BEV self-driving architectures by designing deep learning models for object detection, semantic segmentation, and voxel grid occupancy in BEV frameworks. Integrate BEV representations into end-to-end planning and control pipelines. Establish BEV level tracking capabilities. Contribute to behavior-level ML models by designing models for learned actor prediction, fusing object tracking and actor prediction, and learned trajectory planning models. Develop efficient pipelines for large-scale data processing and annotation (pseudo-labeling) of sensor data (e.g., LiDAR point clouds, image frames). Implement data augmentation, synthetic data generation, and domain adaptation strategies to improve model robustness. Collaborate with conversion and deployment teams to ensure seamless integration and deploy ML models on edge devices with real-time performance and resource efficiency. Optimize inference pipelines for embedded and automotive-grade hardware. Work with robotics, software, and hardware engineering teams to ensure seamless integration of perception systems and with product/operations teams to define performance metrics and improve reliability. Contribute to the model development roadmap and provide mentorship and guidance to junior team members. What you’ll need to Succeed
Bachelor's degree in computer science, data science, artificial intelligence or related field with 6+ years of professional experience or a master's degree with 4+ years of experience. Expertise and applied experience in monodepth and multiview depth estimation. Experience in the autonomous vehicle (AV) industry. Theoretical and practical understanding of machine learning for at least one of the following areas: depth estimation/segmentation; 3D BEV space modeling; actor prediction; learned trajectory planning; autonomous driving end-to-end modeling; vision, LiDAR and radar-based object detection and classification; multimodal multitask learning; calibration, odometry, localization; and tracking. Experience with understanding data distributions and analyzing long-tail distributions. Mastery of Python and PyTorch, with ability to transition research code to production-ready standards. Proficiency with Ray. Bonus points
PhD in machine learning or data science. Proficient in writing CUDA kernels and developing custom PyTorch operations. Experience with NVIDIA libraries and frameworks such as CuDNN, CUBLAS, and NPP. Perks of Being a Full-time Torc’r
Torc cares about our team members and provides benefits to support health, work/life balance, and growth. Our culture is collaborative and team-focused. Torc offers: A competitive compensation package that includes a bonus component and stock options. 100% paid medical, dental, and vision premiums for full-time employees. 401K with a 6% employer match. Flexible schedule and generous paid vacation (available immediately after start date). Company-wide holiday office closures. AD&D and Life Insurance. Hiring Range for Job Opening
US Pay Range: $177,300—$212,800 USD Location: Ann Arbor, MI
#J-18808-Ljbffr
Torc is a leader in autonomous driving, focused on developing software for automated trucks to transform how the world moves freight. Torc has a long history in autonomous vehicle technology and is part of the Daimler family. What you’ll do
Develop and optimize computer vision, LiDAR and radar-based ML models, including monocular and stereo depth estimation algorithms. Understand objects, lanes, obstacles, and weather conditions within the driving environment. Enhance perception systems to process multi-modal sensor data effectively. Use data science techniques to analyze model performance, data distributions, and identify corner cases. Contribute to BEV self-driving architectures by designing deep learning models for object detection, semantic segmentation, and voxel grid occupancy in BEV frameworks. Integrate BEV representations into end-to-end planning and control pipelines. Establish BEV level tracking capabilities. Contribute to behavior-level ML models by designing models for learned actor prediction, fusing object tracking and actor prediction, and learned trajectory planning models. Develop efficient pipelines for large-scale data processing and annotation (pseudo-labeling) of sensor data (e.g., LiDAR point clouds, image frames). Implement data augmentation, synthetic data generation, and domain adaptation strategies to improve model robustness. Collaborate with conversion and deployment teams to ensure seamless integration and deploy ML models on edge devices with real-time performance and resource efficiency. Optimize inference pipelines for embedded and automotive-grade hardware. Work with robotics, software, and hardware engineering teams to ensure seamless integration of perception systems and with product/operations teams to define performance metrics and improve reliability. Contribute to the model development roadmap and provide mentorship and guidance to junior team members. What you’ll need to Succeed
Bachelor's degree in computer science, data science, artificial intelligence or related field with 6+ years of professional experience or a master's degree with 4+ years of experience. Expertise and applied experience in monodepth and multiview depth estimation. Experience in the autonomous vehicle (AV) industry. Theoretical and practical understanding of machine learning for at least one of the following areas: depth estimation/segmentation; 3D BEV space modeling; actor prediction; learned trajectory planning; autonomous driving end-to-end modeling; vision, LiDAR and radar-based object detection and classification; multimodal multitask learning; calibration, odometry, localization; and tracking. Experience with understanding data distributions and analyzing long-tail distributions. Mastery of Python and PyTorch, with ability to transition research code to production-ready standards. Proficiency with Ray. Bonus points
PhD in machine learning or data science. Proficient in writing CUDA kernels and developing custom PyTorch operations. Experience with NVIDIA libraries and frameworks such as CuDNN, CUBLAS, and NPP. Perks of Being a Full-time Torc’r
Torc cares about our team members and provides benefits to support health, work/life balance, and growth. Our culture is collaborative and team-focused. Torc offers: A competitive compensation package that includes a bonus component and stock options. 100% paid medical, dental, and vision premiums for full-time employees. 401K with a 6% employer match. Flexible schedule and generous paid vacation (available immediately after start date). Company-wide holiday office closures. AD&D and Life Insurance. Hiring Range for Job Opening
US Pay Range: $177,300—$212,800 USD Location: Ann Arbor, MI
#J-18808-Ljbffr