Data Scientist

Data Scientist - CricViz - London

CricViz has established itself as a market leader in the collection, analysis and dissemination of data across the world’s leading cricket competitions, with the largest and most sophisticated database in world cricket. Our work spans several verticals, including Performance Analysis, Broadcast and Media, and Fantasy and Gaming platforms. Customers include the BBC, Sky, Sony, ECB, and IPL-winning RCB.

Job Description:

We are seeking a highly skilled Data Scientist to join the CricViz team. This pivotal role focuses on the end-to-end development of proprietary metrics and predictive models derived from the world’s most sophisticated cricket databases. You will lead the transformation of complex, high-frequency tracking data into market-leading, commercial-grade analytical products. Your work will empower sophisticated professional clients by surfacing match state insights and player performance indicators not captured by conventional analysis. The ideal candidate is an experienced Data Scientist/Quantitative Analyst with strong problem-solving skills, capable of working professionally within an evolving and fast-paced environment.

Key Responsibilities:

Technical Expertise: Minimum 3 years of experience in data science or quantitative research, with a proven track record of handling large-scale, high-granularity sports datasets, spatiotemporal event data, and raw tracking feeds (e.g., ball-tracking, telemetry).

Predictive Modeling & ML: Deep proficiency with the PyData stack (Python, pandas, numpy, scikit-learn, XGBoost, LightGBM) and advanced machine learning methods including neural networks, random forests, time-series analysis, and feature engineering.

Database & Workflow Infrastructure: Working knowledge of SQL databases, version control (Git), and cloud environments (AWS/GCP) to handle complex, high-frequency data pipelines.

Analytical Domain Knowledge: Professional-level understanding of cricket match dynamics, tactical analytics, and the variables influencing match state outcomes (e.g., Win Probability, expected metrics like xR/xW).

Key Requirements

Technical Expertise: A minimum of 3 years experience in data science, with a proven track record of handling large-scale, high-granularity sports datasets and feeds.

Predictive Modeling: Deep proficiency with the PyData stack (pandas, numpy, scikit-learn, XGBoost) and advanced machine learning methods including neural networks and random forests.

Analytical Domain Knowledge: A professional-level understanding of cricket match dynamics and the factors influencing match state outcomes.

Nice-to-haves

Tracking Data Experience: Prior experience working with high-frequency tracking or GPS data to create aggregated, value-add insights.

Strategic Communication: Ability to translate highly technical modeling concepts into clear commercial value propositions for sophisticated stakeholders.

Discretion & IP Management: Experience working in sensitive commercial environments where protecting proprietary modeling work is paramount

Equality and Diversity

CricViz is committed to building an open and inclusive culture that supports personal development and learning. Ellipse believes in the principle of equal opportunity in employment and its employment policies for recruitment, training, development and promotion despite any differences based on individual grounds of race, colour, nationality, religion or belief, sex, sexual orientation, marital status, age, ethnic and national origin, disability or gender reassignment.

Benefits

25 days holiday (plus bank holidays)

Hybrid working with regular time spent at our offices in London

Company pension scheme

Eye Test Contribution

Life Insurance

Training and Development Opportunities

About Ellipse

CricViz is part of Ellipse, a leading sports data and analytics company comprising CricViz,

FootballViz, Horse Racing, RugbyViz (Oval and Stuart Farmer Media Services), and TennisViz.

Working with the world’s biggest broadcasters, professional teams, and rights holders, we

simplify complex data to engage a broad and diverse audience and tell better stories about the

sports we love