Principal Computer Vision Engineer

Catapult Sports•Boston, MA

1d•Hybrid

About The Position

Catapult is seeking a Principal Computer Vision & Tracking Engineer to lead the computer vision and real-time tracking systems for their camera-based products. This role involves managing a small team, developing the perception stack for athlete performance insights, and working with technologies like neural network inference on edge AI accelerators, 3D object tracking, and data science. The position requires a broad skill set, including optimizing models for edge inference, designing movement analysis algorithms, and analyzing data for athlete profiles. The engineer will report to a Senior Director of Engineering and will play a player-coach role, collaborating with embedded platform and applications teams. This is an opportunity for someone with experience in real-time perception systems that operate reliably in real-world conditions.

Requirements

8+ years of software engineering experience, with significant depth in at least one of: computer vision, real-time systems, ML/AI deployment, or robotics perception.
Strong proficiency in Python and C/C++ – you're comfortable across the full stack from model training to performance-critical native code.
Demonstrated experience shipping ML or CV systems to production, especially on resource-constrained or embedded platforms.
The ability to own ambiguous problems end-to-end: scoping, prototyping, shipping, and measuring.
Comfort with leadership: you've mentored engineers, led technical direction, or driven cross-team initiatives, even if your title didn't say "lead."

Nice To Haves

Deeper knowledge of the mathematics behind tracking systems: 3D geometry, camera models, state estimation, filtering, optimization.
Experience with edge AI accelerators and inference optimization libraries.
Background in pose estimation, human movement analysis, or biomechanics.
Experience with depth cameras (structured light, time-of-flight) and 3D perception.
Familiarity with embedded Linux, Docker on ARM, and systems-level debugging.

Responsibilities

Own the technical direction of our computer vision and tracking domain: the full pipeline from sensor readings through computer vision, motion recognition, and metric calculation.
Lead and mentor a small team (1–2 engineers), setting priorities, reviewing designs, and driving execution while remaining deeply hands-on.
Train, optimize, and deploy neural networks for real-time segmentation and classification on embedded hardware, including model conversion and optimization for edge accelerators.
Extend our tracking and motion recognition pipeline to support new movements and types of analysis.
Own the reliability of the domain: analyze tracking accuracy, build quality metrics, and use data to drive improvements across the pipeline.