Robotics Perception Intern
Gritt Robotics is developing physical AI to automate outdoor construction, starting with the construction of renewable energy infrastructure. The founding team comprises experts in robotics and AI from Carnegie Mellon, Stanford and MIT. Gritt is backed by top VCs who have previously funded Uber, Notion and Lyft.
About the role
We’re looking for a perception/computer vision intern to join our team. As an intern, you will play a pivotal role in building the perception stack that powers our robots and enables our on-field operations. You will work on challenging problems in 2D and 3D perception in outdoor environments. You'll need to thrive in a fast-paced, dynamic startup environment where you'll wear multiple hats and have a direct impact on our product's evolution. Ideally, you have a proven track record of building, training, and deploying computer vision models (both 2D and 3D) for robotic applications, and you're passionate about pushing the boundaries of what's possible in robotics with AI.
This will be an internship for one of two durations: 3 months, or 6 months.
We offer competitive salaries, and the opportunity to work on a mission with tremendous climate impact.
What you’ll get to work on
Develop and deploy 2D and 3D perception models for robotic applications in outdoor construction.
Scale our data collection infrastructure from already deployed fleet of robots
Build dashboards for performance metric tracking and model improvements.
Work on bridging sim-to-real gap and enabling training perception models from purely synthetic data.
Develop and improve data pipelines, training and validation infrastructure.
Optimize training and inference times/memory footprint on GPUs.
What we look for
M.S/Ph.D degree in robotics, vision, computer science, mechanical engineering, electrical engineering or other engineering disciplines (or equivalent experience).
2+ years of hands-on experience developing 2D and 3D perception models for robotics applications.
Experience with building software that was deployed on robots operating in physical world.
Extensive experience with Python and common frameworks like PyTorch.
Should be comfortable taking ownership of tasks with light supervision.
Must have excellent problem-solving skills.
Legally authorized to do an internship in the United States for either 3 months or 6 months.