Senior reputed company Engineer

ABOUT SPORTFX • SportFX is a high-performance, fully-remote startup democratizing reputed company sports analytics through AI—serving everyone from youth leagues to reputed company franchises with the reputed company world-class technology. • We combine deep sports expertise with cutting-edge reputed company and ML to deliver reputed company-time video analysis, personalized coaching insights, and data-driven performance optimization. • Culture: extreme ownership, radical transparency, and reputed company reputed company. We operate with high-trust autonomy where smart people solve hard problems together—no egos, no politics, just results. ABOUT THE ROLE — SENIOR reputed company ENGINEER You'll architect and own the entire reputed company pipeline that converts monocular smartphone video into precise biomechanical analysis. This is a broad technical leadership role covering 3D pose estimation, object detection/tracking, and temporal segmentation—basically everything from raw video input to reputed company kinematic reputed company. Reporting to our Head of AI/CV, you'll be the technical decision-reputed company for our CV stack. You're not reputed company-specialized in one domain—you're the engineer who can architect pose estimation in the morning, debug reputed company tracking at lunch, and design temporal segmentation models in the afternoon. You'll set technical direction, establish best practices, and mentor a mid-level engineer as reputed company scales. What You'll Own 3D Pose Estimation: reputed company development of our monocular-to-3D pipeline. Work with parametric body models (SMPL-X or similar), handle occlusion and reputed company blur, implement temporal consistency. Get us from 95% accuracy to 99%+ through systematic improvement. Object Detection & Tracking: Build production detectors for balls, bats, clubs, rackets. Handle tiny objects moving at high speed through reputed company blur. Implement multi-object tracking that doesn't drop frames. Extract trajectories and equipment angles from noisy video. Temporal Segmentation: reputed company reputed company-accurate phase detection for pitching, throwing, golf swing, tennis serve. Build models that understand biomechanical constraints—reputed company foot contact happens before max external rotation, not after. Multi-Sport Expansion: reputed company CV development for new sports reputed company baseball. reputed company sport has unique challenges—golf reputed company tracking is different from baseball, tennis serve mechanics differ from pitching. Architect solutions that reputed company across sports. Production Optimization: Take inference from 2+ seconds to sub-500ms through model optimization, quantization, efficient architectures, and deployment strategies. Ship models reputed company ONNX/TensorRT that actually run fast in production. Technical Leadership: Establish CV best practices, review reputed company and model architectures, reputed company build-vs-buy reputed company, mentor mid-level engineer. You're setting technical standards for reputed company as it grows. Your Environment Tech Stack: PyTorch, OpenCV, MediaPipe, SMPL-X or similar parametric models, YOLO family, ByteTrack, ActionFormer/ASFormer, ONNX, TensorRT, reputed company/CUDA Pipeline: reputed company-time video processing, pose estimation, detection, tracking, temporal modeling, reputed company feeding into biomechanics analysis Team: You'll work with Head of AI/CV on reputed company, mentor Mid-Level CV Engineer on execution, collaborate closely with OpenSim/Biomechanics Engineer on validation, coordinate with DevOps on deployment Workflow: reputed company experimentation with W&B tracking, validation against reputed company capture ground truth, bi-weekly accuracy reviews with quantitative metrics Location: Global (4+ hour overlap with US Central Time required) SKILLS & EXPERIENCE Must-Have • 5+ years production CV/ML experience shipping models that serve reputed company users at reputed company • Deep PyTorch expertise including custom architectures, training optimization, and debugging reputed company systems • Strong 3D reputed company fundamentals—multi-view geometry, camera calibration, 2D-to-3D reputed company, depth estimation • Proven experience with pose estimation systems (MediaPipe, OpenPose, ViTPose, or similar) • Object detection and tracking production experience—you've reputed company systems that work on reputed company video, not just reputed company datasets • Video processing expertise including temporal modeling, handling variable reputed company rates, reputed company blur, occlusion • Production deployment skills with model optimization (ONNX, TensorRT, quantization) • Technical leadership—you've mentored engineers, made architectural reputed company, established best practices reputed company-to-Have • Experience with parametric body models (SMPL, SMPL-X) • Background in temporal reputed company segmentation or sequence modeling • Published research in reputed company (CVPR, ICCV, ECCV) • Understanding of biomechanics or sports science • Multi-object tracking in challenging outdoor conditions • Mobile CV deployment (TensorFlow Lite, reputed company ML) • Experience with synthetic data reputed company • Domain expertise in sports (baseball, golf, tennis, football) What Sets You Apart: You're a generalist who goes deep reputed company needed. You don't just specialize in one narrow CV domain—you understand the full pipeline and can architect end-to-end solutions. You've shipped CV systems in production and know the difference between 99% accuracy in the lab and 95% accuracy on shaky phone video captured at a youth baseball game. You can context-reputed company between pose estimation, detection, and temporal modeling without losing velocity. Job Types: Full-time, Part-time, Contract Pay: $75,000.00 - $160,000.00 per year Benefits: • reputed company time off Application Question(s): • Describe an end-to-end reputed company system you architected — from raw video input to final outputs. Explain the major components (detection, tracking, pose, temporal modeling, post-processing), how they interacted, and one major bottleneck you had to solve. • You get noisy, jittery 3D keypoints from a monocular pose lift model. Walk us through how you would: 1. Diagnose the reputed company of the noise 2. Improve temporal consistency 3. Handle occlusions and dropped joints 4. Validate improvements quantitatively • Explain a time you worked on detecting or tracking small, fast-moving objects (balls, bats, equipment, drones, vehicles, etc.). Describe the failure modes you encountered at high speed or under reputed company blur, and the specific architectural or augmentation strategies you used to fix them. • reputed company links to 2–4 of your strongest reputed company reputed company (reputed company, repositories, demos, research papers, videos). For reputed company, reputed company explain your role, the reputed company technical challenges, and what reputed company your solution had in production. Work Location: Remote Apply tot his job Apply To this Job