Deep Reinforcement Learning Intern for Autonomous Driving Safety – Reinforcement Learning

Job Description

Reinforcement Learning Planning Research Intern | PlusAI

The Tone:
This is an internship at PlusAI, located in Silicon Valley with operations in the United States and Europe. PlusAI is a Physical AI company pioneering AI-based virtual driver software for factory-built autonomous trucks. This role is crucial for ensuring the absolute safety of autonomous vehicles by developing a Safety-Critical Trajectory Correction (STC) module that acts as a real-time safety overlay. The intern will directly contribute to accelerating the deployment of next-generation autonomous trucks.

The TL;DR
• Role: Internship
• Type: Seasonal/Temporary
• Location: In-person, Silicon Valley
• Pay: $19–$65 hourly
• Mission: Design, train, and validate a Safety-Critical Trajectory Correction (STC) architecture using Deep Reinforcement Learning to provide a continuous, constrained safety barrier for the vehicle fleet.
• Tech Stack: PyTorch, Tensorflow, Jax

What You’ll Actually Do
• Develop: Own the development of a Safety-Critical Trajectory Correction (STC) module, which will function as a real-time safety overlay to intercept and minimally perturb intended trajectories upon collision risk detection.
• Design & Validate: Design, train, and validate the STC architecture using Deep Reinforcement Learning to establish a continuous, constrained safety barrier for the autonomous vehicle fleet.
• Research: Conduct groundbreaking research with the potential to significantly impact PlusAI’s autonomous driving products, specifically focusing on reinforcement learning to generate safe trajectories, leading to publishable results.
• Benchmark: Develop and benchmark cutting-edge deep learning techniques relevant to autonomous vehicle planning and safety systems.
• Integrate: Collaborate with team members to optimize and seamlessly integrate the developed techniques into the production perception or autonomous vehicle (AV) stack.

The Must-Haves
• Background: Pursuing a Master of Science (MS) or Doctor of Philosophy (PhD) in Computer Science (CS), Electrical Engineering (EE), mathematics, statistics, or a related field.
• Experience: Possess 1-2 years of experience in implementing and training models within at least one deep learning framework, such as PyTorch, Tensorflow, or Jax.
• Skills: Demonstrate a thorough understanding of reinforcement learning principles and applications.
• Bonus: Prior experience in the design, implementation, and training of deep reinforcement learning models; or previous involvement in projects related to autonomous driving.