Senior Data Scientist, Delivery Consumer Discovery

Job Description

We’re looking for an experienced Data Scientist to own the ranking and recommender systems behind how customers discover what to order on Bolt Food.

Your work shapes what each customer sees first on the home screen and across other personalised surfaces, and you’ll take ideas from research all the way into production.

About us

With over 200 million customers across 50+ countries and 850+ cities, Bolt is one of the fastest-growing tech companies in Europe and Africa — powered by 4.5+ million partners on our platform, 4,000+ employees globally. And it's all thanks to our people.

We believe in creating an inclusive environment where everyone is welcome, regardless of race, colour, religion, gender identity, sexual orientation, national origin, age, or ability.

Our ultimate goal is to make cities for people, not cars — and we need your help on this mission!

About the role

You will work on the core systems that help customers find the right restaurants, stores, dishes, and items across Bolt Food. Your initial focus will be the home screen and other personalised screens: which categories and carousels each customer sees, in what order, and what appears within them. You will also shape how the full surface is optimised, balancing customer relevance against business objectives and guardrails, and contribute to recommendations elsewhere in the customer journey.

This is a highly applied role where you will work closely with product, engineering, analytics, and operations teams to take ideas from research and offline evaluation to online experiments and production systems used by millions of customers.

Main tasks and responsibilities

• Improve ranking and recommendations for the home screen and other personalised screens. This covers learning-to-rank for categories and merchants, personalised recommenders, cold-start and exploration, and screen assembly.
• Build recommendations that help customers discover new restaurants, stores and items.
• Turn business targets and guardrails into ranking objectives without sacrificing customer relevance (multi-objective and full-surface optimisation).
• Design and run A/B tests to measure the impact of ranking and personalisation changes.
• Take models from research to production with Product, Engineering, Analytics and ML Platform (Python, SQL, Spark, Docker, AWS/SageMaker, Airflow), then monitor them.
• Shape technical direction (candidate generation, features, logging, experimentation tooling). Explore sequential and generative recommenders, and ship them only where they earn their complexity. Use AI coding tools (Codex, Cursor, Claude Code) to move faster.

Requirements

• 5+ years in Data Science and ML, ideally building products at a tech company. At this level, we expect you to drive technical direction, not only to deliver models.
• Hands-on with large-scale ranking, recommender or personalisation systems. Search and IR experience is a plus.
• Strong Python and SQL, plus PyTorch and the core ML stack (Pandas, NumPy, scikit-learn).
• Experience with several of: learning-to-rank, collaborative filtering, two-tower or sequential models, embeddings and vector search, gradient boosting, multi-objective optimisation. You don’t need all of them.
• Solid grounding in experimentation, statistical inference, and offline and online evaluation, with strong product sense for turning ambiguous problems into measurable solutions.
• Has built ML systems end to end and drives projects from problem discovery to production impact. Comfortable aligning stakeholders when customer experience trades off against commercial targets.

Company offers

• Accelerate your professional growth with unique career opportunities.
• Enjoy a rewarding salary and stock options, knowing that as Bolt succeeds, so do you.
• Take care of your physical and mental health with our wellness perks.
• Celebrate 5 years at Bolt with a 1-month paid sabbatical to recharge.
• Connect with colleagues at annual company events and smaller team gatherings.
• Work on-site at our Tallinn HQ, next to the operations and engineering teams whose decisions you automate.