Senior Computer Vision Scientist – Basketball Tracking

SkillCorner SAS; Paris; On-site; EUR 90,000 - 130,000; Full time

Job summary

SkillCorner SAS in Paris is seeking a Senior Computer Vision Scientist to join our Basketball Tracking team. You will bring deep expertise in deep learning to models powering our basketball tracking data, from detection and tracking to re-identification, recognition and pose estimation.

You will own key models end to end, designing architectures, building training and evaluation pipelines, and pushing performance to production-grade quality. This role blends applied research with live deployment.

Qualifications

• Strong deep learning expertise in people tracking, re-identification and pose estimation.
• Experience shipping detection/tracking models to production.
• Data-centric work: dataset curation and handling noisy labels.

Responsibilities

• Design, train and optimize state-of-the-art deep learning models for detection, tracking and pose estimation.
• Own key components of the basketball tracking pipeline end to end.
• Make architectural decisions and push research to production-grade quality.
• Monitor state of the art, analyze performance and implement improvements.
• Collaborate with teams and translate client needs into tracking improvements.

Skills

Deep learning in CV

Python

PyTorch

TensorFlow

AWS

Docker

Re-identification

Object detection

Tracking

3D geometry

Education

Graduate degree or PhD in engineering or computer science

Tools

OpenCV

CUDA

GCC

Job description

About SkillCorner

At SkillCorner, we turn a single broadcast camera feed into rich sports data, 100% automatically. Our Computer Vision and Machine Learning algorithms detect every player, the ball and the referees, locate them on the field, track them frame by frame and recognize who is who.

Since 2016, we have grown into a global leader in our field. We cover more than 150 men’s and women’s competitions, hold over 100 billion data points on more than 100,000 professional players, and are trusted by more than 350 football, basketball and American football teams. Clubs, federations and agencies use our data to rethink how they analyze performance, scout and recruit.

We are a team of about 150 people around the world, with our tech team based mostly in Paris. The Computer Vision team, 16 people strong, sits at the heart of our mission: it uses state-of-the-art deep learning to deliver precise, high-quality tracking data, at scale and in production.

The role

We are looking for a Senior Computer Vision Scientist to join our Basketball Tracking team, reporting to the Team Lead. You will bring deep expertise in deep learning to the models that power our basketball tracking data, from detection and tracking to re‑identification, recognition and pose estimation.

You will own key models end to end: designing architectures, building training and evaluation pipelines, and pushing performance to production‑grade quality. You will make architectural decisions with real downstream impact and help raise the research and engineering standards of the team.

This role sits where applied research meets production. Your work will go from experiment to live deployment, used by the professional basketball teams SkillCorner works closely with around the world.

What you’ll do

Deep learning research and development

• Design, train and optimize state-of-the-art deep learning models (CNNs, Transformers, GNNs) for detection, tracking, re‑identification, recognition and pose estimation

• Own key components of the basketball tracking pipeline end to end, from data and training to evaluation and deployment

• Make and defend architectural decisions, grounded in a solid understanding of the theory behind the models you build

• Monitor the state of the art, analyze model performance and turn new ideas into concrete improvements

• Establish the metrics and tooling that measure tracking quality, and drive continuous improvement from one release to the next

Engineering excellence

• Bring research algorithms into our AWS production pipeline and keep performance stable when new models go live

• Optimize models for accuracy, speed and cost at scale

• Raise the bar on engineering and research practices: code reviews, testing, reproducible experiments, documentation and smart use of LLM‑based tools

• Investigate issues in the pipeline and keep code quality high

• Understand client needs and product stakes, and translate them into concrete tracking improvements

• Share your knowledge and support more junior team members as they grow

A graduate degree or PhD in engineering, computer science, mathematics or a related field4+ years of hands‑on experience in computer vision with deep learning, including production systemsStrong deep learning expertise in areas such as people tracking, re‑identification, people, face and object recognition, camera calibration, body pose estimation and action recognitionProven experience designing, training and shipping detection, tracking or recognition models to production, not only research prototypesExperience with data‑centric work: dataset curation, annotation strategies and handling noisy labelsA strong grasp of the theory behind modern architectures (CNNs, Transformers, GNNs), and the judgment to choose between approachesExperience assembling several algorithms into one reliable systemThe ability to drive technical decisions independently and explain trade‑offsStrong Python for ML: clean, tested, deployable code, with PyTorch or TensorFlow and OpenCVHands‑on experience with AWS workflows and DockerExcellent communication skills in EnglishNice to haveFrench: a strong plus, as the team is French‑speakingExperience with multi‑object tracking and re‑identification in crowded scenes, or with sports or broadcast videoExperience with camera calibration, homography estimation or 3D geometryExperience running ML pipelines at scale in the cloud (GPU inference, batch processing)Notions of MLOps and model optimizationExperience using LLM‑based agents to speed up development, debugging or supportPublications at top computer vision or ML venues (CVPR, ICCV, ECCV, NeurIPS)Knowledge of, or a genuine interest in, basketball

Why join us

Real impact: your work ships to production and is used by more than 350 professional teams worldwideHard, exciting problems: state‑of‑the‑art computer vision on real broadcast video, at scaleOwnership: own key models end to end and shape how our tracking technology evolvesA great team: passionate people at the crossroads of AI and sport, with a tech team in the heart of Paris