Data Scientist

S-PRO

full-time

Posted on: 9/23/2025

Origin: • 🇨🇭 Switzerland

✨ AI Apply

Mid-LevelSenior

AirflowBigQueryCloudDockerNumpyPandasPythonScikit-LearnSQL

About the role

Conduct deep exploratory data analysis on historical ticket sales, movie schedules, attendance trends, and promotional campaigns.
Build robust pricing models and demand forecasting tools considering time, location, movie type, holidays, and social media buzz.
Develop optimization algorithms for showtime scheduling across multiple screens and locations.
Analyze promotional campaign effectiveness and build attribution models to optimize future marketing spend.
Engineer relevant features from transactional, demographic, and behavioral data.
Create initial PoC models and pipelines for pricing, scheduling, and promotions optimization.
Collaborate with business and operations teams to define KPIs and translate business challenges into modeling tasks.
Deliver interactive dashboards (Streamlit or similar) and reports to visualize model outputs and business insights.
Document the model logic, assumptions, and performance for both technical and non-technical audiences.

3+ years of experience in Data Science roles with a proven track record of implementing production-level ML solutions.
Uplift modelling
Strong Python programming (Pandas, NumPy, scikit-learn, XGBoost, Pyomo/OR-Tools for optimization).
Experience in pricing strategies, time series forecasting, or operations research.
Solid SQL skills for data extraction, transformation, and aggregation.
Understanding of consumer behavior analytics and A/B testing methods.
Experience with interactive data visualization tools (Plotly, Dash, Streamlit).
Ability to quickly build and iterate on PoC solutions to validate ideas and showcase value.
Mathematical background
Applied statistics
Nice to have: Experience with optimization in ticketing, entertainment, or retail industries.
Nice to have: Familiarity with causal inference techniques and marketing mix models.
Nice to have: Exposure to deployment tools (Docker, Airflow) and cloud data platforms (e.g., BigQuery, Snowflake).
Ability to work across teams and present to stakeholders with different technical backgrounds.