About the role
At ReSpo.Vision, were revolutionizing football with AI. Our Deep Learning models and Computer Vision algorithms transform single-camera video feeds into rich 2D and 3D data, enabling full 3D reconstruction of real games (you can think of it as FIFA-like replays) and extracting deep tactical and player performance insights. Were building a next-level interactive platform for sports analytics that combines expert analysis with LLM-derived insights.
Were seeking a Junior to Mid-level Data Engineer/Scientist to work on cutting-edge soccer tracking data algorithms and automated analytics. Youll process and analyze large datasets of soccer-related information as we transition to an interactive platform. We need a football enthusiast who can develop robust, scalable pipelines to extract valuable insights from game data.
We value innovation and provide autonomy to explore various methodologies. We expect you to be highly motivated and capable of delivering results with little supervision. If youre passionate about AI and sports, thrive in a dynamic startup environment, and want to contribute to cutting-edge AI projects, wed love to hear from you. Join us in creating innovative tools that will shape the future of soccer analysis!
Our Philosophy
- Modular Design -> framework & modules, interconnected but decoupled
- Code Reviews -> thorough review process
- Testing -> unit tests for critical code, functional tests for modules, e2e tests for the system
- CI/CD -> test, build and deploy with every iteration
- Dev + Staging + Prod environments -> deploy new features quickly, ensure stability for client deployments
- Documentation -> comprehensive description of the process for reference and easy onboarding
- Scalability -> decoupling, statelessness (where possible), automation
- Bleeding Edge Tech -> leverage the latest & greatest tools and models where possible, create your own when not
Our Tech Stack
- Environment -> poetry + docker
- DL -> Pytorch, Pytorch lightning, neptune.ai
- Data -> numpy, pandas
- Configuration -> Hydra
- Data Validation -> Pydantic + pandera
- Workflows -> Kubernetes + Argo Workflows
- Cloud -> GCP
- CI/CD -> Gitlab
Responsibilities
- Develop and maintain data pipelines for processing soccer tracking data
- Implement machine learning models for automated soccer analytics
- Optimize existing algorithms to reach web-ready performance
- Collaborate with cross-functional teams to improve data quality and accessibility
- Assist in the creation of data visualizations
Requirements
- Bachelors or Masters degree in Computer Science, Data Science, or related field
- 1-3 years of experience in data engineering or data science
- Proficiency in Python and SQL
- Experience with data processing libraries such as Pandas
- Familiarity with machine learning concepts and libraries (e.g., Scikit-learn, Pytorch, Numpy)
- Knowledge of cloud platforms (GCP/AWS)
- Experience with version control systems (Git)
- Excellent problem-solving skills and attention to detail
- Strong communication skills and ability to work in a collaborative environment
Nice to have
- Experience with data visualization libraries (e.g., Matplotlib, Plotly, D3.js)
- Knowledge of JavaScript for front-end data integration
- Familiarity with computer vision libraries like OpenCV
- Understanding of soccer/football tactics and analytics
Benefits
- Dynamic start-up environment with interesting scientific challenges & bleeding edge technology and models (this time for real)
- Opportunity to build real-world deployable machine and deep learning-based products changing the world of Football
- International projects & collaborations with top Football Clubs & Federations
- Ability to directly influence development direction of a product
- Office in the strict center of Warsaw
- Private medical care and Multisport
