Machine Learning Engineer II - Learned Planning (Reinforcement Learning)
About this role
Developing and training machine learning models for learned behavior systems occupies the daily focus of this position, including behavior cloning, imitation learning, and reinforcement learning. Team members build, validate, and improve the machine learning models and infrastructure that power decision-making for autonomous trucks, working alongside perception, prediction, planning, and safety engineering groups.
Torc Robotics created this role to support automated freight operations and enable safe, efficient, and human-like driving in real-world environments. Engineers who thrive here typically possess strong Python and PyTorch skills alongside a solid background in applying ML techniques to robotics or complex control systems.
What you will do
- Develop and train machine learning models for learned behavior systems using behavior cloning, imitation learning, and reinforcement learning.
- Implement production-quality machine learning code to support model training, evaluation, and inference within the autonomy stack.
- Analyze model performance, diagnose failure modes, and propose improvements to increase robustness and generalization across various scenarios.
- Contribute to model training pipelines and data workflows by curating behavior datasets derived from simulation, fleet logs, and on-vehicle data.
- Collaborate closely with simulation, validation, and autonomy engineering teams to test and evaluate learned behavior models across diverse driving environments.
- Help integrate learned behavior models into simulation and testing workflows to enable faster iteration and comprehensive validation.
- Support the development of tooling and infrastructure that improves experimentation speed, reproducibility, and overall model iteration.
What you need
- Hold a Bachelor's degree in Computer Science, Robotics, Electrical Engineering, Machine Learning, or a related technical field with four or more years of industry experience, or a Master's degree with at least two years of experience.
- Demonstrate practical experience applying machine learning techniques such as imitation learning, reinforcement learning, or sequence modeling to robotics, autonomous systems, or complex control environments.
- Possess strong programming skills in Python and PyTorch, backed by experience writing production-quality machine learning code.
- Demonstrate experience training and evaluating machine learning models using large datasets and scalable compute environments.
- Show an understanding of machine learning architectures utilized in autonomy systems, including transformers, graph neural networks, or sequence models.
- Bring proven experience debugging model behavior, analyzing performance metrics, and iterating on training pipelines.
Nice to have
- Experience working in autonomous driving, robotics, or simulation-based training environments.
- Experience with reinforcement learning frameworks or distributed training systems like Ray.
- Experience working with simulation environments or large-scale behavior datasets.
- Familiarity with vehicle dynamics, motion planning, or multi-agent decision-making systems.
- Experience deploying machine learning models into production or real-world robotics systems.
Benefits
- 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 the start date
- AD+D and Life Insurance
Skills and tech stack
Questions candidates ask
What is the remote work policy for this role?
The position is open to remote work within the United States. Additionally, the company is open to hiring in the Ann Arbor, Michigan office in a hybrid capacity.
What is the salary range for this position?
The hiring range for the US pay range is $153,200 to $183,800 USD. Total compensation also includes a corporate bonus and stock option plan.
What technologies and frameworks will I be using?
The role requires strong programming skills in Python and PyTorch. Experience with reinforcement learning frameworks or distributed training systems like Ray is also listed as a bonus.
What kind of team will I be working with?
You will work closely with teams across perception, prediction, planning, and safety. The culture is collaborative, energetic, and team-focused.