Autonomous Driving RL Research Scientist

DeepRoute; Fremont (CA); On-site; USD 150,000 - 210,000; Full time

Job summary

DeepRoute in Fremont, CA is pioneering end-to-end autonomous driving systems powered by reinforcement learning. You will apply RL in closed-loop, safety-critical environments, leveraging large-scale simulation and real-world driving data to improve safety and robustness.

The role centers on training and deploying RL policies, scaling training with parallel simulations, designing reward functions, and advancing sim-to-real transfer while collaborating with cross-functional teams to productionize

Qualifications

• Experience training and deploying RL policies in autonomous driving contexts.
• Strong background in Python and PyTorch with scalable ML pipelines.
• Familiarity with sim-to-real transfer and domain randomization.

Responsibilities

• Train and deploy RL policies in closed-loop driving environments.
• Scale RL training using massively parallel simulation systems.
• Design and optimize reward functions for complex driving behaviors.
• Improve sim-to-real transfer for real-world robustness.
• Collaborate with cross-functional teams to integrate models into production systems.

Skills

DQN

PPO

SAC

TD3

RLHF

Python

C++

PyTorch

Ray

Horovod

Reward modeling

Sim-to-real

CUDA

Domain randomization

Traffic rules

Tools

Ray

Horovod

Job description

DeepRoute in Fremont, CA is pioneering end-to-end autonomous driving systems powered by reinforcement learning. You will apply RL in closed-loop, safety-critical environments, leveraging large-scale simulation and real-world driving data to improve safety and robustness.

The role centers on training and deploying RL policies, scaling training with parallel simulations, designing reward functions, and advancing sim-to-real transfer while collaborating with cross-functional teams to productionize