Design advanced multi-modal architectures that fuse heterogeneous sensor data (camera, LiDAR, radar, HD maps) into unified spatial representations.
Develop foundational perception models leveraging BEV transformers, voxel-based encoders, or implicit scene representations.
Own large-scale training workflows — from data sampling strategies and augmentation pipelines to distributed training and hyperparameter optimization.
Advance model robustness and generalization, addressing long-tail conditions such as low visibility, occlusions, and rare scene configurations.
Establish evaluation frameworks for geometric accuracy, temporal stability, and cross-domain transfer performance.
Collaborate cross-functionally with sensor calibration, mapping, and fusion teams to ensure cohesive perception model interfaces.
Mentor and guide ML engineers, cultivating best practices in experimentation, code quality, and model validation.
Stay at the forefront of ML research, exploring self-supervised learning, large-scale pretraining, or foundation models for 3D perception.
What You'll Need to Succeed
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 related field (or equivalent practical experience).
Proven expertise in BEV modeling, 3D scene understanding, and multi-view fusion.
Strong background in multi-modal sensor fusion, particularly integrating camera and LiDAR data.
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 leadership in driving ML model innovation and mentoring technical teams.
Bonus Points
Experience with autonomous driving or robotics perception in production environments.
Experience with MLOps and infrastructure tools (Ray).
Hands-on expertise in BEV-based ML architectures, LiDAR-vision fusion, or spatial-temporal modeling.
Familiarity with 3D labeling, calibration, and sensor simulation pipelines.
Track record of publications or open-source contributions in top-tier venues (CVPR, ICCV, NeurIPS, ICRA, CoRL).
Understanding of performance tradeoffs and deployment constraints (latency, memory, accuracy).
Work Location: For this position, we are open to hiring in Ann Arbor, MI in a hybrid capacity. We are also open to hiring Remote in the United States.
Perks of Being a Full-time Torc’r
Torc cares about our team members and we strive to provide benefits and resources to support their health, work/life balance, and future. Our culture is collaborative, energetic, 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 plan with a 6% employer matchFlexibility in schedule and generous paid vacation (available immediately after start date)Company-wide holiday office closures
AD+D and Life Insurance
At Torc, we’re committed to building a diverse and inclusive workplace. We celebrate the uniqueness of our Torc’rs and do not discriminate based on race, religion, color, national origin, gender (including pregnancy, childbirth, or related medical conditions), sexual orientation, gender identity, gender expression, age, veteran status, or disabilities.
Even if you don’t meet 100% of the qualifications listed for this opportunity, we encourage you to apply.
Our compensation reflects the cost of labor across several geographic markets. Pay is based on a number of factors and may vary depending on job-related knowledge, skills, and experience. Torc's total compensation package will also include our corporate bonus and stock option plan. Dependent on the position offered, sign-on payments, relocation, and other forms of compensation may be provided as part of a total compensation package, in addition to a full range of medical, financial, and/or other benefits.
Job ID: 102945
Hiring Range for Job Opening
US Pay Range
$215,500—$258,600 USD
