Computer Vision Engineer

We are hiring a Computer Vision Engineer to build and improve sports video intelligence models including detection, tracking, pose estimation, and event understanding. The role focuses on CV research and applied modeling, with collaboration on data and platform teams.

• Build and train CV models for sports video: player/ball detection, multi-object tracking, pose/keypoints, event/action recognition, identity association (re-ID).
• Own the experimentation loop: hypotheses, ablations, error analysis, measurable improvements.
• Design and maintain evaluation: task-appropriate metrics, dataset slices, failure taxonomy.
• Improve data efficiency: augmentations, sampling strategies, handling label noise, weak/self-supervision.
• Prototype modern architectures (transformer-based detection/tracking, temporal models, multi-task setups).
• Collaborate on dataset and labeling design, productionize models, add quality gates.

• Strong applied CV experience with hands-on model development.
• Solid PyTorch skills: training loops, debugging, data pipelines, DDP basics.
• Comfort with video CV fundamentals: occlusion, identity switches, temporal consistency, calibration, domain shift.
• Strong Python engineering and bias toward measurable outcomes.