Torc Robotics
Machine Learning Engineer, II - 3D Perception
About this role
Torc is seeking a Machine Learning Engineer II specializing in 3D perception for autonomous trucks. You'll develop and optimize bird's eye view perception models using multi-modal sensor data, working collaboratively to integrate production-ready ML solutions into the autonomy stack.
What you'll do
- Design and improve machine learning models for autonomous truck perception systems
- Own end-to-end model development from data preparation through evaluation and production integration
- Write production-quality Python and PyTorch code for scalable training and inference workflows
- Analyze model performance, identify failure modes, and improve robustness and generalization
- Collaborate with software engineers and autonomy teams to integrate perception models into larger systems
- Mentor junior ML engineers and contribute to improvements in training pipelines and experimentation tooling
What they're looking for
- Python and PyTorch
- 3D perception and computer vision
- Multi-modal sensor fusion (camera, LiDAR)
- Bird's Eye View (BEV) perception
- Machine learning model development and evaluation
- Production ML systems and deployment
- Data analysis and troubleshooting
- Autonomous driving systems
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Torc Robotics
Torc Robotics develops autonomous driving software and systems for trucks. The company is hiring systems engineers, software engineers, and test automation specialists to build validation frameworks, integration environments, and web applications that ensure the reliability and quality of their autonomous vehicle technology.
- Website
- torcrobotics.com
Likely interview questions
- Walk us through your experience developing 3D perception models—what sensors have you worked with and what were the key challenges?
- Describe a time when a production ML model failed in unexpected ways. How did you diagnose and fix it?