Senior Data Scientist, Growth

What You’ll Be Doing

• Design, build, maintain, and improve lifetime value prediction models across ARQ’s countries and acquisition channels.
• Work closely with Growth & Marketing, Product, Finance, Data Engineering, and Engineering teams to understand business needs and translate them into modelling solutions.
• Help evaluate acquisition quality by channel, campaign, geography, customer segment, and product behaviour.
• Build models that support better decisions around growth spend, payback periods, customer quality, retention, and long term value.
• Analyse large scale customer, product, marketing, and transaction datasets to identify patterns, risks, and opportunities.
• Continuously monitor model performance and improve accuracy, reliability, and business impact over time.
• Create clear frameworks and metrics that help teams understand the trade-offs behind growth decisions.
• Partner with Data Engineering and Engineering teams to productionise models, pipelines, and reporting where needed.
• Bring a pragmatic approach to modelling, balancing technical depth with commercial impact.
• Over time, contribute to other Data Science challenges across Growth and the wider business.

What You’ll Need

• 5+ years in Data Science, Machine Learning, Applied Statistics, Analytics, or a related discipline.
• Experience building prediction models in a consumer business (B2C, D2C), ideally around LTV, growth, acquisition, retention, churn, monetisation, or customer value.
• Strong Python skills and experience working with large scale datasets.
• Solid understanding of supervised learning techniques, model evaluation, feature engineering, and statistical tradeoffs.
• Able to translate ambiguous commercial questions into structured data science problems.
• Strong business judgement and the ability to connect model outputs to real decisions.
• Experience working cross-functionally.
• Clear communication skills, especially when explaining modelling assumptions, limitations, and recommendations to non-technical stakeholders.
• Comfortable operating in a fast-moving environment with high ownership and evolving priorities.
• Familiarity with MLOps, model monitoring, experiment design, causal inference, or incrementality measurement (nice to have).