About the Role
Design and implement machine learning models for autonomous driving systems using imitation and reinforcement learning. Build scalable training pipelines, analyze model performance, and integrate models into simulation and real-world testing environments while collaborating with engineering teams to improve system robustness and deployment efficiency.
Responsibilities
- Design and train machine learning models for end-to-end perception and planning tasks, utilizing techniques like imitation learning and reinforcement learning.
- Write production-grade code in Python to support model training, evaluation, and inference within autonomous systems.
- Evaluate model performance, detect failure cases, and implement changes to improve generalization across diverse driving scenarios.
- Develop and maintain data pipelines for model training, sourcing data from simulation, vehicle logs, and fleet recordings.
- Work closely with simulation, validation, and autonomy teams to assess model behavior in varied driving conditions.
- Integrate end-to-end models into simulation platforms to accelerate testing and validation cycles.
- Support the creation of tools and infrastructure that enhance reproducibility, experimentation speed, and model iteration.
- Participate in technical discussions on model architecture choices and training methodologies.
Requirements
- Bachelor’s degree in Computer Science, Robotics, Electrical Engineering, Machine Learning, or a related field with at least four years of relevant industry experience, or a Master’s degree with two or more years of experience.
- Hands-on experience applying machine learning methods such as computer vision, imitation learning, or reinforcement learning to robotics or autonomous systems.
- Proficient in Python and PyTorch, with a track record of writing clean, production-level machine learning code.
- Experience training and evaluating models using large-scale datasets and distributed computing environments.
- Familiarity with modern end-to-end model architectures including BEV transformers, Vision-Language-Action (VLA) models, or diffusion-based approaches.
- Skilled in diagnosing model issues, interpreting performance metrics, and refining training workflows.
- Proven ability to work effectively with cross-functional teams to embed ML models into complex software stacks.
Nice to Have
- Background in autonomous vehicles, robotics, or simulation-driven training systems.
- Experience with reinforcement learning frameworks such as Ray or similar distributed training platforms.
- Knowledge of Vision-Language-Action (VLA) models or neural rendering techniques.
- Understanding of vehicle dynamics, motion planning algorithms, or multi-agent interaction systems.
- Prior experience deploying machine learning models into production or real-world robotic applications.
Tech Stack
Python, PyTorch, BEV models, Transformers, Diffusion models, VLA (Vision-Language-Action), Reinforcement Learning, Imitation Learning, Ray, Distributed Training, Simulation Systems, Autonomy Stack, Large-Scale Data Processing
Compensation
Not specified
Work Arrangement
Not specified
Team
Collaborative environment involving simulation, validation, and autonomy engineering teams focused on developing and refining end-to-end machine learning models for autonomous driving.
Not specified
