Data Scientist

Role overview

Responsibilities

• check_circle Lead the development and deployment of ML/AI solutions including embedding models, fine-tuned LLMs, and ranking systems that drive engagement and orders while raising the bar for technical excellence.
• check_circle Apply generative AI and LLM techniques to personalisation challenges, generating customer and partner representations that improve search relevance and app experiences.
• check_circle Own your results by designing, running and interpreting A/B experiments with statistical rigour, measuring real impact on business metrics and holding yourself accountable.
• check_circle Collaborate with ML engineers to productionise models, implementing MLOps best practices and maintaining monitored pipelines that deliver consistent value.
• check_circle Break down silos by translating complex business questions into clear modelling approaches and communicating results effectively to product and commercial stakeholders.
• check_circle Be determined to take end-to-end ownership of well-scoped workstreams, independently framing problems, choosing approaches, running experiments and presenting findings.
• check_circle Move fast by writing production-quality Python code and efficient SQL for data pipelines and analyses that can scale across our marketplace.
• check_circle Contribute to JET's foundation model platform and personalised targeting systems, pushing boundaries to create lasting impact across millions of customer interactions.
• check_circle Set clear goals by designing experiments that influence commercial decisions while ensuring statistical validity and actionable insights.
• check_circle Aim higher by staying current with advances in search, retrieval, recommendations and LLM applications, bringing fresh ideas to drive the AI Growth vision forward.

Basic qualifications

• Proven track record delivering end-to-end ML solutions from problem framing through data exploration to production deployment and experiment measurement, demonstrating your commitment to achieving goals.
• Hands-on expertise in search, retrieval and recommendation techniques including embedding-based approaches, learning-to-rank, and vector similarity search with measurable business impact.
• Practical experience applying LLMs in production environments, including prompt engineering, fine-tuning, structured output validation and assessing generative output quality.
• Strong experimentation skills with ability to design and interpret A/B tests, reason about statistical significance, and understand the gap between offline and online performance.
• Production-grade Python coding abilities that go beyond notebooks, writing clean, testable code suitable for engineering workflows and collaboration with technical teams.
• Proficient SQL skills across complex data warehouses, including partitioning, window functions, and large-table joins, with focus on query efficiency and data quality.
• Excellent problem-framing and communication skills to translate ambiguous business questions into modelling approaches and explain technical results to non-technical stakeholders based on respect and mutual support.
• Self-starter attitude comfortable with autonomy and ambiguity, thriving in fast-paced environments where you can build rapidly, test rigorously and roll out successes at scale.
• Strong collaboration skills to work effectively with senior data scientists, ML engineers, product partners and commercial teams across different levels and functions.
• Results-driven mindset with attention to detail, able to balance speed of execution with technical rigour while making data-informed decisions that create lasting impact.

Preferred qualifications

• Experience with causal inference or uplift modelling relevant to promotions and growth initiatives.
• Knowledge of sequential or session-based recommendation modelling techniques.
• Familiarity with real-time data pipelines and streaming infrastructure.
• Experience working across multiple languages or markets in a data science context.

About the company