Internship, Perception Software Engineer, Tesla Bot (Fall 2024)

Tesla is on a path to build humanoid bi-pedal robots at scale. As a member of the software team, you will design and implement reliable & efficient code for classical or learned robotics, specifically applying to perception, calibration, locomotion, object detection, and more. You will work on improving the robot's behavior in the real world, reflecting those capabilities in a simulation engine for evaluations and faster iterations. The code you will write will be deployed to our fleet of humanoid robots.

• Build, integrate, and deploy real-time state-of-the-art perception models and algorithms into existing system architecture

• Develop online and offline state estimation algorithms by fusing information from cameras, IMUs, and other sensors

• Validate and document performance of algorithms and models in real and simulated environments

• Create robust sensor calibration routines that perform reliably in complex and unpredictable environments

• Train machine learning and deep learning models on a computing cluster for visual recognition & perception tasks

• Currently pursuing a degree in Computer Science, Robotics, or a related field with a gradation date between 2024 - 2025

• Proficient in C++ or Python

• Strong background in core robotics fundamentals, such as kinematic/dynamic modeling, Bayesian state estimation (e.g., MAP, MMSE, MLE), 3D reconstruction, structure-from-motion, visual odometry, visual inertial odometry, bundle adjustment

• Excellent software and computing fundamentals