Principal Machine Learning Engineer

ReSpo.Vision is an AI and Computer Vision company transforming how sports are analyzed, visualized, and monetized. Our proprietary single-camera system extracts elite-level tracking data and performance analytics from standard broadcast or tactical video, without wearables or in-venue installations. Already used by global clubs, federations like FIFA, Concacaf, or CONMEBOL and for competitions like Euro or Copa America, we are actively expanding into media, fan engagement, and betting applications.

Our pipeline combines advanced computer vision and deep learning models to track all players and the ball in 3D using a single-camera feed. The resulting positional data powers our growing product suite: from match analytics platform to visual content, including 3D match reconstructions (see an early demo: YouTube) and real-time broadcast augmentation with dynamic stats and virtual overlays. The system is built for scalability, leveraging cloud-native infrastructure, GPU inference pipelines, and sports-specific post-processing modules that turn raw detections into meaningful insights.

We’re now entering an exciting phase, pushing our tracking system toward real-time applications, lowering latency to enable live insights and instant visual augmentations. In parallel, we’re building new layers on top of our core data, including realistic 3D match reconstructions and virtual overlays for enhanced broadcast experiences.

Your Role

As a Principal Machine Learning Engineer at ReSpo.Vision, you'll transform product ideas into novel AI-powered sports experiences by building them yourself. This is a hands-on position where you'll implement models, write production code, and construct entire systems from the ground up. You'll own product initiatives from conception through deployment, personally coding at the intersection of cutting-edge ML, real-time systems, and product innovation.

You will be responsible for:

1. Product-Driven Technical Leadership: Translate ambitious product visions (real-time augmentations, new analytics products, 3D reconstructions) into concrete technical architectures and personally drive their implementation
2. End-to-End System Architecture: Design and implement complete ML systems: data pipelines, training infrastructure, real-time inference, the whole thing
3. Real-Time ML Infrastructure: Architect and build low-latency systems that push our tracking from post-game to live applications, enabling instant broadcast augmentations and in-game insights
4. Technical Product Strategy: Partner with product and business teams to identify new opportunities where our core system can unlock novel experiences; contribute to the product roadmap
5. Autonomous Initiative Ownership: Drive entire product verticals independently - from framing ambiguous problems to shipping production systems that serve multiple clients
6. Cloud-Native ML Platform: Build scalable, reproducible ML workflows on AWS/GCP, including distributed training pipelines, GPU inference optimization, and sports-specific post-processing modules
7. Innovation at Scale: Pioneer new approaches in sports computer vision while ensuring systems scale to process hundreds of matches across global competitions

Who You Are

-You've spent 5+ years building ML systems in production (not just training models in notebooks)

-You're equally comfortable discussing product strategy and debugging distributed training jobs

-Computer vision is your thing - detection, segmentation, maybe even some 3D reconstruction

-You can take a vague idea and turn it into a technical plan without much hand-holding

-You actually enjoy the full stack: data engineering, ML pipelines, cloud infrastructure, API design

-You are a PyTorch expert, cloud native, and you know how to fully utilize multiple GPUs

-You have at least some experience building real-time systems and solving low-latency challenges

-You are excited about or at least have some knowledge about sports, preferably football (soccer)

Core Technical Requirements

-Strong experience building end-to-end ML pipelines in the cloud

-Strong software engineering fundamentals and system design skills

-Experience with real-time/streaming systems and low-latency optimization

-Track record of shipping ML products that handle production scale and complexity

-Experience optimizing ML systems for production - GPU utilization, distributed computing, etc.

-Effective use of LLM-based tools (Copilot, Cursor, Claude, ChatGPT etc.) to accelerate development and research workflows

Nice to have

-Experience with 3D graphics, reconstruction, or AR/VR applications

-Background in video streaming, broadcast technology, or media systems

-Knowledge of sports analytics, media & entertainment vertical or gaming/betting platforms

-Contributions to open-source ML projects or published research

-Experience with YOLO, Detectron2, or the Hugging Face ecosystem

What we offer

-A chance to work with a top-tier engineering team, including Kaggle Grandmasters

-Hybrid work model

-Flexibility in employment type (B2B/contract of employment)

-Market-competitive salary

-Private healthcare and Multisport card

-Open training budget – we’ll support your development in relevant areas

-Ownership and autonomy – no micromanagement, real impact

-A unique opportunity to shape a globally recognized, high-impact product used by top sports organizations like Chelsea, Paris Saint-Germain, or FIFA