Data Scientist

Data Scientist / ML Engineer | Databricks, MLOps & Recommendation Systems Location: London (hybrid) Contract length: 4 months Initial Day rate: Up to £545 per day Engagement: Outside IR35 contract About the rol eWe're recruiting a senior Data Scientist / ML Engineer for a Databricks platform buildout with an international events company. This is a hands-on delivery role covering three interconnected workstreams: MLOps foundations, a recommendation engine for exhibitors and sessions, and identity resolution across sparse customer registration data . You'll be responsible for both defining the ML approach and building it end-to-end, setting the standards (MLOps patterns, feature engineering conventions, model lifecycle, matching logic) that the internal team will operate and extend after you hand ove r. What you'll be do • ingDesigning and implementing an MLOps framework end-to-end: model tracking, versioning, promotion, serving, monitoring, and feedback ingest • ionDesigning, experimenting with, and implementing a recommendation approach for exhibitors and sessions based on attendee preferen • cesBuilding a tiered matching pipeline (deterministic + fuzzy) for a single customer view, including feature engineering and a human-in-the-loop feedback l • oopSetting ML standards and conventions the client team can follow independen • tlyOwning documentation: MLOps reference architecture, feature specifications, matching rules, model runbo • oksRunning knowledge transfer sessions so the internal team can operate, extend, and iterate without external supp ort What we're looking • for5+ years in applied ML/data science with strong hands-on production deli • veryProven end-to-end ownership of at least one ML delivery: design through productionisa • tionProduction experience with MLOps on Databricks (or a directly comparable platform) — MLflow, Feature Store, model serving, monitoring, drift detec • tionProduction experience building recommendation systems or embedding-based retrieval, ideally with vector se • archProduction experience with entity resolution / fuzzy matching pipelines (Jaro-Winkler, Levenshtein, Soundex or equivalent, plus blocking strategies for sc • ale)Strong hands-on Python (PySpark, pandas, ML libraries) and • SQLWorking experience with Delta Lake, Unity Catalog, and Lakeflow • JobsExperience with Git-based CI/CD for ML pipelines (Databricks Asset Bundles, GitHub Actions, or equival • ent)Prior customer-facing or consulting experience, comfortable running knowledge transfer and leaving a team self-suffic ient Nice to • haveExperience building lightweight UIs on Databricks Apps for human-in-the-loop work flows