SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 215,500 - 258,600 / annual
Torc Robotics, now part of the Daimler family, is seeking a Staff Machine Learning Engineer to lead the development of next-generation Bird's-Eye View (BEV) and multi-modal perception models for autonomous truck technology. This is a technical leadership role focused on model innovation and architectural advancement, not downstream feature integration.
You will lead BEV model development by defining and executing the technical roadmap for BEV-based perception models across multiple tasks including detection, segmentation, road topology, and scene understanding. You'll design advanced multi-modal architectures that fuse heterogeneous sensor data (camera, LiDAR, radar, HD maps) into unified spatial representations, leveraging BEV transformers, voxel-based encoders, or implicit scene representations.
Key responsibilities include owning large-scale training workflows from data sampling strategies and augmentation pipelines to distributed training and hyperparameter optimization. You will advance model robustness and generalization by addressing long-tail conditions such as low visibility, occlusions, and rare scene configurations. You'll establish evaluation frameworks for geometric accuracy, temporal stability, and cross-domain transfer performance.
Cross-functional collaboration is essential—you'll work with sensor calibration, mapping, and fusion teams to ensure cohesive perception model interfaces. As a technical leader, you'll mentor and guide ML engineers, cultivating best practices in experimentation, code quality, and model validation. You'll stay at the forefront of ML research, exploring self-supervised learning, large-scale pretraining, and foundation models for 3D perception.
Required qualifications include 10+ years of experience in deep learning for perception, 3D vision, and/or autonomous systems, with an M.S. or Ph.D. in Computer Science, Electrical Engineering, Robotics, or related field. You must have proven expertise in BEV modeling, 3D scene understanding, and multi-view fusion, with a strong background in multi-modal sensor fusion, particularly integrating camera and LiDAR data. Proficiency in Python and deep learning frameworks (PyTorch or TensorFlow) is essential, along with experience in large-scale data pipelines, distributed training, and experiment management systems.
Bonus qualifications include autonomous driving or robotics perception in production environments, MLOps and infrastructure tools (Ray), hands-on expertise in BEV-based ML architectures and LiDAR-vision fusion, familiarity with 3D labeling and sensor simulation pipelines, and a track record of publications or open-source contributions in top-tier venues (CVPR, ICCV, NeurIPS, ICRA, CoRL).
