Reinforcement Learning Intern

Intuitive•Sunnyvale, CA

1d•$62 - $82•Onsite

About The Position

The Reinforcement Learning Intern will report to the future forward research lead and contribute to developing and evaluating reinforcement learning (RL) algorithms for supervised autonomy initiatives. The intern will identify, train, and test RL algorithms using data collected from Intuitive surgical robot systems. Most of the work will use offline-collected data rather than real-time robot data, with real-time deployment as a stretch goal. The intern will collect tele-operated simulation and/or real robot data during realistic exercises, train and benchmark off-the-shelf RL algorithms, and adapt algorithms to the surgical domain. Based on experimental results, the intern will recommend an algorithm and experimental setup for future work, present findings to the broader team, and may deploy a selected algorithm in simulation or on the dV5 to validate real-time performance. This is a full-time, 10–12-week internship starting in May or June. The position is fully onsite and has a day shift. Compensation is hourly, with listed pay ranges varying by region, and includes benefits and a housing allowance.

Requirements

Must be currently enrolled in and returning to an accredited, degree-seeking academic program after the internship.
Must be available to work full-time, approximately 40 hours per week, for 10–12 weeks starting in May or June; specific start dates are shared during recruiting.
Currently enrolled in a doctorate-level Engineering (such as Biomedical or Electrical Engineering), Robotics, Computer Science, or related degree-seeking program.

Nice To Haves

Deep experience with a deep learning framework such as PyTorch or JAX.
Strong familiarity with reinforcement learning algorithms, such as policy gradient or actor-critic methods.
Willingness to learn about robotics and the application of reinforcement learning to surgical robotics.
Strong written and verbal communication skills for explaining experiment motivation, findings, and implications.
Experience with video-based and multimodal data analysis and processing.

Responsibilities

Collect tele-operated simulation and/or real surgical robot data while performing realistic exercises, such as a Fundamentals of Laparoscopic Surgery pick-and-place task.
Train off-the-shelf reinforcement learning algorithms on trajectory data and benchmark performance using established metrics.
Adapt reinforcement learning algorithms to the surgical domain and exercise of interest, and identify techniques to improve performance compared with off-the-shelf models.
Recommend an algorithm and experimental setup for subsequent work based on experimental results, and present findings to the broader team.
Deploy a chosen reinforcement learning algorithm in simulation or on the dV5 to validate its performance in real time, if pursued.