ML Engineer - Reconstruction

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.

We're seeking a Reconstruction Engineer to join Peripheral's Reconstruction team, helping push the state of the art in 3D reconstruction, neural rendering, and spatial models (monocular depth estimation, multi-view stereo, and beyond). You'll report to our Senior Reconstruction Engineer and work primarily on the research side of the team, developing and evaluating new approaches, with exposure to how the most promising results make their way into Peripheral's core pipeline.

This is a role for someone who has already done serious research in this space and wants to see their work move beyond the paper: someone who can run rigorous experiments independently, while learning what it takes to turn a strong result into something reliable enough to run at scale.

You've done research in 3D reconstruction, neural rendering, or related spatial modeling problems, and you have the publication record to show for it. You're comfortable going from a new idea or paper to a working implementation and an honest evaluation of whether it holds up.

You think carefully about the full spectrum of spatial understanding, from classical multi-view geometry to neural approaches like NeRFs and Gaussian splatting, and you have your own opinions about where the field is headed.

You work independently and take ownership of your experiments, but you're also a strong collaborator: you share results openly, welcome feedback, and learn quickly from the people around you.

You're excited by the opportunity to help shape Peripheral's research culture from an early stage: the standards, rigor, and ways of working you help establish now are what the team will build on as it grows.

• Design, run, and analyze experiments across 3D reconstruction, neural rendering, and spatial models (monocular depth estimation, multi-view stereo, NeRF/Gaussian-splatting-style approaches, etc.).

• Implement and evaluate new techniques from the research literature and from your own ideas, and report results clearly to the team.

• Help move promising research into production by profiling, optimizing, and handing off models in a form the rest of the team can build on.

• Master's or PhD in Computer Science, Robotics, Computer Vision, or a related field.

• Publication(s) at a top-tier venue (e.g., CVPR, ICCV, ECCV, NeurIPS, 3DV) in 3D reconstruction, neural rendering, or spatial modeling, as a first author or major contributor.

• Strong research experience in 3D reconstruction and spatial modeling, across both classical (multi-view geometry, structure-from-motion) and neural (implicit representations, neural rendering) approaches.

• Proficiency in Python and a deep learning framework, with a track record of implementing and training models from scratch.

• Strong communication skills, able to explain results and trade-offs clearly to both researchers and engineers.

• Candidates must have the legal right to work in Canada and be willing to relocate to…