WHO WE ARE:
Peripheral is developing spatial intelligence, starting in live sports and entertainment. Our models generate spatial data, used for advanced sports analytics and immersive media experiences. We’re solving key research challenges in 3D computer vision, creating the foundations for the next generation of robotic perception and embodied intelligence.
We’re backed by top investors, including Khosla Ventures, Inovia, Deloitte Ventures, Daybreak, and Entrepreneurs First, and working with some of the biggest names in sports. Our team includes engineers and researchers from leading technology companies and research institutions, and we’re building technology at the intersection of AI, graphics, and the future of live entertainment. We’re ambitious and looking to win.
THE OPPORTUNITY:
We're seeking a Reconstruction Engineering Intern to join Peripheral's Reconstruction team, contributing to the models and systems that turn raw multi-sensor capture into rich, usable 3D understanding of the world. You'll work on problems spanning 3D reconstruction, neural rendering, and spatial modeling, from early experimentation through to work that helps move promising approaches closer to production.
You'll work closely with engineers on the team, contributing to real research and engineering problems and getting exposure to how Peripheral bridges cutting-edge reconstruction techniques with a production system.
WHO YOU ARE:
You're currently pursuing a degree in Computer Science, Robotics, Computer Vision, or a related field, and you have a genuine interest in 3D reconstruction, neural rendering, or spatial modeling (e.g., monocular depth estimation, multi-view stereo, NeRFs, Gaussian splatting).
You have some experience implementing or experimenting with computer vision or ML models, whether through coursework, research, or personal projects, and you're comfortable with the underlying math (multi-view geometry, linear algebra, optimization).
You're curious and self-directed: you like digging into a problem, trying an approach, and honestly evaluating whether it's working. You're an excellent communicator of your thoughts and ideas, and you're diligent in keeping documentation so ideas don't get lost.
You're excited to learn from a team working at the intersection of research and production, and to contribute real work during your internship.
WHAT YOU'LL BE DOING:
Support experiments in 3D reconstruction, neural rendering, or spatial modeling, under the guidance of engineers on the team.
Help implement, test, and evaluate new techniques from research literature or internal ideas.
Contribute to tooling or infrastructure that helps the team run experiments and evaluate results more efficiently.
Assist with productionizing promising research results, e.g., profiling, optimizing, or integrating a model into existing systems.
Analyze and visualize model outputs to help diagnose failure modes and identify areas for improvement.
Document your work and share findings with the team as you go.
REQUIREMENTS:
Currently pursuing a Bachelor's or Master's degree in Computer Science, Robotics, Computer Vision, or a related field.
Foundational understanding of 3D computer vision or spatial modeling concepts (e.g., multi-view geometry, structure-from-motion, or neural rendering), through coursework, research, or personal projects.
Solid grasp of foundational ML concepts (e.g., gradient descent, loss functions, overfitting/regularization, model evaluation), whether from coursework or personal projects.
Experience implementing or training ML models (e.g., through coursework, research, or personal projects).
Proficiency in Python and familiarity with PyTorch.
Candidates must have the legal right to work in Canada for the duration of the internship and be based in or willing to relocate to Toronto for an in-office role. At this time, we are unable to provide immigration sponsorship.
NICE TO HAVE:
Familiarity and experience with neural rendering techniques (e.g., NeRFs, 3D Gaussian splatting).
Experience with SLAM frameworks, point cloud processing, or 3D reconstruction libraries (e.g., COLMAP, Open3D, PCL).
Familiarity with how GPUs work and some CUDA experience — writing or reading kernels, profiling, or general awareness of memory bandwidth vs. compute trade-offs.
Publications, coursework projects, or research experience relevant to 3D reconstruction or spatial modeling.
Experience with large-scale data pipelines (multi-camera/LiDAR capture, calibration).
Prior internship or research experience in computer vision or robotics.
WHY YOU'LL LOVE WORKING HERE:
High ownership of high-impact projects shaping the future of spatial intelligence and 3D media.
Mentorship from world-class engineers and researchers.
Unparalleled access to premier global sporting events and iconic venues.
Flexible Paid Time Off (PTO).
