[Job description]
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, and competitions like FIFA or CONMEBOL, 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 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.
As an ML Engineer at ReSpo.Vision, you’ll play a key role in shaping products, enabling real-time, visually engaging experiences across sports and media.
[You will be responsible for]
- Designing, training, testing, and validating machine learning models for classification,
- regression, object detection, and segmentation
- Choosing appropriate architectures and optimization techniques
- Performing data quality analysis, feature engineering, and experimentation
- Preparing ML models for deployment in production environments
- Developing robust MLOps pipelines for training, testing, and monitoring
- Writing clear documentation and conducting peer code reviews
- Participating in ML system architecture planning and data strategy development
[Who You Are]
- A proactive ML Engineer with a strong academic background and commercial experience
- Skilled in PyTorch with 3–4 years of practical application
- Comfortable working with Linux and cloud environments (AWS or GCP)
- Experienced in working with image and video data, including detection and segmentation tasks
- Capable of owning end-to-end ML projects, from data to deployment
- Fluency in English and Polish (written and spoken)
- Analytical, autonomous, and comfortable with uncertainty and iteration
[Additional Preferred Qualifications]
- Knowledge of Hugging Face libraries ecosystem, YOLO and Detectron
- Experience with scalable ML systems and low-latency inference
- Interest in sport analytics and complex data environments
[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)
- Private healthcare, Multisport card
- Open training and development budget aligned with your career goals
- A unique opportunity to shape a globally recognized, high-impact product used by top sports organizations like Chelsea, Paris Saint-Germain, or FIFA
- Ownership and autonomy – no micromanagement, real impact
