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 an ML Engineering Intern to join Peripheral's motion capture team, helping deploy, maintain, and improve the systems that power our player pose outputs. Our markerless pose estimation system takes in multiview video and extracts human keypoints, identities, and other spatial information from the scene in real time, and you'll help make that system easier to run in production and better over time.
You'll spend your internship focused on three things: deploying and supporting our models in the cloud, curating and improving the data that trains them, and helping iterate on the models themselves. You'll work closely with the motion capture team's evaluation tools to understand where the system falls short and help close those gaps.
WHO YOU ARE:
You're currently pursuing a degree in Computer Science, Electrical Engineering, Robotics, or a related field, and you have a strong foundation in 3D computer vision, including camera calibration, multi-view geometry, and 3D coordinate transforms, whether from coursework, research, or personal projects.
You're comfortable with Python and at least one deep learning framework, and you're interested in the practical side of ML: getting models running reliably in production, not just training them.
You're curious about cloud infrastructure and deployment (containers, cloud platforms, CI/CD); prior exposure is a plus, but we're just as excited about someone eager to learn how production ML systems are actually run.
You have an eye for data quality: you can look at a dataset or a model's outputs and reason about what's wrong and why.
You're excited to learn on the job, ask questions, and contribute real work to a live production system during your internship.
WHAT YOU'LL BE DOING:
Help deploy and maintain our pose estimation models in cloud infrastructure, working on containerization, deployment pipelines, and monitoring.
Curate, clean, and analyze training data, working with the team to identify gaps or quality issues in existing datasets.
Support incremental improvements to existing pose estimation models, running experiments and evaluating results against real-world accuracy.
Use evaluation tools to diagnose failure modes in the pose estimation system and help prioritize what to fix.
Work with the motion capture team to understand how camera setup, calibration, and data pipeline choices affect downstream model performance.
Document your work and contribute to the team's data and deployment tooling as you go.
REQUIREMENTS:
Currently pursuing a Bachelor's or Master's degree in Computer Science, Electrical Engineering, Robotics, or a related field.
Strong foundation in 3D computer vision fundamentals, including camera calibration, multi-view geometry, and 3D coordinate transforms (e.g., through coursework, research, or personal projects).
Proficiency in Python and familiarity with a common deep learning framework.
Strong attention to detail, particularly when working with data.
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:
Some exposure to cloud platforms (AWS or GCP), or strong interest in learning cloud deployment and infrastructure.
Experience with containerization or orchestration tools (e.g., Docker, Kubernetes).
Experience with data labeling, annotation tools, or dataset versioning.
Familiarity with pose estimation concepts specifically (keypoint estimation, triangulation, multi-object tracking).
Experience with model optimization techniques (e.g., quantization, distillation) for speeding up inference.
Experience with ROS 2 or other robotics middleware.
Prior internship or project experience deploying an ML model end to end.
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).
