Data Scientist

Competitive salary dependent on experience. Company performance-related bonus, healthcare insurance & wellbeing benefits.

About Liv-ex: We offer a multitude of business services covering trading opportunities, data, logistics and various automation technologies; aimed at a diverse group of wine businesses, from ambitious young start-ups to established merchants and traders. Our aim is to make the wine trade more transparent, efficient and safe, for the benefit of our members and the market as a whole. We are hardworking, committed and action oriented, retaining a valued neutrality in the market. Founded in 2000, Liv-ex has grown to serve a growing number of members in the B2B sector, with an ever-expanding range of services. We help our members and other stakeholders to better understand the fine wine market and identify profit opportunities.

Summary Purpose: We’re seeking a Data Scientist to join our growing data team and drive the development of machine learning systems that power our wine exchange and data platform. You’ll work on challenging problems at the intersection of NLP, recommendation systems, and time-series forecasting, building production-grade ML solutions that directly impact our merchants’ trading decisions and operational efficiency. This role offers the opportunity to work on cutting-edge AI/ML projects including semantic search systems, hybrid recommendation engines, and predictive models, all applied to the unique domain of fine wine trading.

Responsibilities:

• Design, develop, and deploy machine learning models for complex NLP tasks including entity matching, semantic search, and text classification.
• Build and maintain recommendation systems combining collaborative filtering, content-based filtering, and business rule layers.
• Develop time-series forecasting models to predict market trends, pricing dynamics, and merchant behaviour.
• Fine-tune and deploy transformer-based models (BERT, sentence transformers, cross-encoders) for production use.
• Implement ML pipelines on cloud infrastructure (AWS, Databricks) using PySpark for large-scale data processing.
• Work with vector databases for semantic search and similarity matching at scale.
• Collaborate with engineers to integrate ML models into production systems via REST APIs and batch processing.
• Conduct A/B testing and develop evaluation frameworks to measure model performance and business impact.
• Write clean, maintainable, production-quality code following software engineering best practices.

What We’re Looking For:

• 3+ years in data science or ML engineering, taking projects from research to production.
• Bachelor’s degree or higher in a quantitative field (e.g., Computer Science, Mathematics, Statistics, Physics; PhD welcome).
• Strong foundation in statistical learning, classical ML (e.g., random forests, gradient boosting), and model evaluation/validation.
• Hands-on experience with modern NLP, including transformer models, embeddings, and semantic search (experience building RAG systems is highly desirable).
• Bonus points: Experience with recommendation systems, time-series forecasting, or fine-tuning models like BERT.
• Excellent Python and SQL skills, with a focus on writing scalable, production-ready code.
• Experience with cloud services (ideally AWS) and collaborative version control (Git).
• Strong software engineering practices, including testing, documentation and transitioning from notebooks to production codebases.
• Bonus points: Proficiency with PySpark, Databricks, and deploying models (MLflow, APIs).
• Highly analytical problem solver who can break down complex issues.
• Excellent communicator capable of explaining technical concepts to non-technical stakeholders and working cross-functionally with product and engineering teams.
• Self-motivated, able to work independently, and prioritise effectively.

Why Join Liv-ex:

• Work on unique ML problems in the fine wine domain with real business impact.
• Collaborative data team environment with opportunities to shape architecture decisions.
• Exposure to the full ML lifecycle from research to production deployment.
• Opportunity to work on multiple project types: NLP, recommender systems, forecasting, and more.