• Ideate, develop and improve machine learning and statistical models that drive Swish’s core algorithms for producing state-of-the-art sports betting products. • Develop contextualized feature sets using specific domain knowledge in soccer. • Contribute to all stages of model development, from creating proof-of-concepts and beta testing, to partnering with data engineering and product teams to deploy new models. • Strive to constantly improve model performance using insights from rigorous offline and online experimentation. • Analyze results and outputs to assess model performance and identify model weaknesses for directing development efforts. • Adhere to software engineering best practices and contribute to shared code repositories. • Document modeling work and present to stakeholders and other technical and non-technical partners.

• Design, build, and validate predictive models (e.g. lead scoring, propensity modelling, forecasting, risk prediction) that inform operational and strategic decisions. • Develop and deploy generative AI solutions, including LLM-powered agents, retrieval-augmented generation (RAG) pipelines, and prompt engineering workflows to automate and enhance business processes. • Translate business problems into well-scoped analytical and modelling projects, working with stakeholders to define success criteria and measurable outcomes. • Perform feature engineering, model selection, hyperparameter tuning, and rigorous evaluation using appropriate statistical and ML techniques. • Productionise models into scalable, maintainable pipelines, collaborating with data engineering to integrate outputs into downstream systems (e.g. CRM, BI tools, operational dashboards). • Monitor model performance post-deployment, manage model drift, and implement retraining strategies. • Communicate findings and model outputs to non-technical stakeholders through clear visualisations, written summaries, and presentations. • Stay current with developments in applied ML and generative AI, and contribute to the team’s knowledge-sharing and capability-building efforts. • Provide guidance, direction, and oversight to one direct report within the Data, Insights & AI team.

• Support the development of predictive models across the student lifecycle, including lead scoring, conversion propensity, retention risk, and demand forecasting. • Assist in building and evaluating generative AI solutions, such as LLM-powered agents, prompt engineering workflows, and retrieval-augmented generation (RAG) pipelines. • Perform exploratory data analysis, feature engineering, and data wrangling to prepare datasets for modelling. • Write clean, well-documented Python code for analysis and model development. • Help productionise models by supporting pipeline development, testing, and integration with downstream systems. • Prepare visualisations, summaries, and presentations that communicate analytical findings and model outputs to non-technical stakeholders. • Contribute to the team’s knowledge base by documenting methods, sharing learnings, and participating in code reviews. • Proactively develop your own skills through structured learning, certifications, and hands-on experimentation.

• Build, maintain, and improve dashboards and reports that give stakeholders clear, timely visibility into performance. • Write and optimise SQL and Python to extract, transform, and analyse data from multiple sources. • Partner with stakeholders to understand their questions, define metrics, and translate requirements into analytics that drive decisions. • Ensure data quality and accuracy through validation, de-duplication, and reconciliation of reporting outputs. • Document analyses and reporting logic, and present findings clearly to both technical and non-technical audiences.