Torc Robotics is seeking a Senior Machine Learning Engineer to develop robust models for road and lane detection, a critical function for enabling AV perception and path planning in their Level 4 autonomous vehicle systems.
Requirements
- Hands on experience with segmentation tasks like lane prediction, free space segmentation, etc.
- State of the Art AV experience with multi-sensor data, especially in perception systems for autonomous vehicles or robotics.
- Mastery of Python and PyTorch, with the ability to transition research level code to production and deployment ready standards
- Proficiency in Python, and familiarity with modern ML Ops tools and GPU-based training.
- Experience with LiDAR, radar, or 3D spatial data processing.
- Knowledge of performance metrics for perception and prediction tasks (IoU, FDE, ADE, mAP).
- Proficient in writing CUDA kernels and developing custom PyTorch operations.
Responsibilities
- Design, train, and deploy deep learning models for road and lane topology prediction, including drivable space, lane boundaries, and intersection structures.
- Build and optimize neural network architectures that leverage multi-modal sensor data (camera, LiDAR, radar) and SD/HD map context.
- Lead model ablation studies, error analysis, and performance validation using large-scale simulation and real-world datasets.
- Develop tooling and workflows to automate training, experimentation, and evaluation of ML models.
- Collaborate with teams across perception, mapping, planning, and systems integration to ensure seamless performance in real-world autonomous driving.
- Mentor junior engineers and contribute to technical leadership within the ML modeling group.
Other
- Prior experience in autonomous driving, robotics, or similar safety-critical domains.
- 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 match
- Flexibility in schedule and generous paid vacation (available immediately after start date)
