Computer Vision Scientist - Real-Time Sports Tracking

SkillCorner SAS; Paris; Sur place; EUR 90 000 - 130 000; Plein temps

Résumé du poste

SkillCorner SAS is seeking a Computer Vision Scientist to join our Computer Vision team. You will bring deep learning expertise in computer vision to improve our automatic tracking data, from detection to re-identification and recognition, and own key models from design to production.

You will work with PyTorch/TensorFlow, OpenCV, and state-of-the-art architectures, shaping research into real-world sports data products used by top football, basketball, and American football teams worldwide.

Qualifications

• PhD or Master’s degree in engineering, CS, math or related field.
• Strong experience in computer vision with deep learning in production.
• Hands-on model training and understanding of architectures beyond pre-trained baselines.
• Proven experience with detection, tracking or recognition pipelines.
• Proficient Python for ML, with PyTorch or TensorFlow and OpenCV.
• Ability to drive technical decisions independently and clearly explain choices.

Responsabilités

• Design, train and optimize deep learning models for detection, tracking, re-identification, and recognition.
• Own components of the tracking pipeline from data to deployment.
• Analyze model performance and translate insights into concrete improvements.
• Establish metrics and tooling to measure tracking quality across releases.
• Integrate research algorithms into AWS production pipelines with stable performance.
• Elevate engineering and research practices through code reviews, testing and reproducible experiments.
• Collaborate with Product, Engineering and Operations to translate client needs into tracking improvements.

Connaissances

Python for ML

English communication

Autonomy

Curiosity

Creativity

Team collaboration

Formation

Graduate degree or PhD in engineering or CS

Outils

PyTorch

TensorFlow

OpenCV

AWS

Docker

Description du poste

SkillCorner SAS is seeking a Computer Vision Scientist to join our Computer Vision team. You will bring deep learning expertise in computer vision to improve our automatic tracking data, from detection to re-identification and recognition, and own key models from design to production.

You will work with PyTorch/TensorFlow, OpenCV, and state-of-the-art architectures, shaping research into real-world sports data products used by top football, basketball, and American football teams worldwide.