Senior Data Scientist: Predictive Operations & Experimentation

Nextbike Polska is hiring a Senior Data Scientist to join the Nextbike City Insights (NCI) team, which builds operational tooling for city bike-sharing networks. The role focuses on predictive modelling and rigorous data analysis to improve city operations through data-driven models and experiments.

• 5+ years of experience building predictive/ML models on operational or time-series data.
• Strong proficiency in Python (pandas, scikit-learn, XGBoost/LightGBM) and SQL; experience with Snowflake data warehouse.
• Experience designing and analysing controlled experiments (A/B tests, quasi-experimental methods).
• Solid grounding in statistics including hypothesis testing, regression, confidence intervals, and power analysis.
• Ability to translate ambiguous business problems into quantifiable hypotheses and measurable outcomes.
• Clear communication skills to present model logic and experiment results to teams and leadership.

Nice to have:

• Experience with geospatial data, mobility/logistics, or marketplace supply-demand problems.
• Familiarity with causal inference techniques (uplift modelling, instrumental variables, synthetic control).
• Exposure to MLOps tools such as MLflow, Airflow, dbt.
• Experience with weather APIs, event data, or external signal sources.
• Background in operations research or optimisation (vehicle routing, scheduling).

Predictive Modelling & Algorithms:

• Design, build, and deploy predictive models for operational challenges such as demand forecasting and predictive rebalancing.
• Integrate heterogeneous signals including historical trip data, weather, events, seasonality, and urban patterns into production-grade feature pipelines.
• Continuously evaluate and iterate on model performance using backtesting and live monitoring.
• Explore and prototype models for maintenance prediction, fleet sizing optimisation, and dynamic pricing sensitivity.

Data Analysis & KPI Development:

• Propose and define KPIs and operational metrics reflecting business impact (e.g., rebalancing cost per trip, station availability rate).
• Perform correlation studies and exploratory analyses to identify actionable patterns.
• Formulate and stress-test hypotheses before live experimentation.
• Build dashboards and automated reports for non-technical stakeholders.

Experimentation & Causal Inference:

• Design rigorous experimentation frameworks (A/B tests, switchback experiments, difference-in-differences) for live city operations.
• Define sample sizes, control groups, and success criteria prior to experiments.
• Analyse experiment results, quantify uplift with confidence intervals, and provide clear recommendations.
• Manage the feedback loop from model to experiment and refinement.
• Address challenges of experimentation in networked systems, including spatial spillover effects and cluster-randomised designs.
• Develop strategies to isolate treatment effects in shared supply and demand networks.
• Apply design-of-experiments principles to constrained environments with operational limitations.