Senior Data Scientist (Advanced Analytics)

About the Role

In this role, you will design and deploy classical machine learning solutions — from time series forecasting and predictive modelling to optimization and dynamic scheduling systems — within SoftServe's AI and Data Science Center of Excellence, a team of 170+ experts, including Data Scientists, ML Engineers, and Architects.

You'll work closely with clients to transform complex tabular and temporal data into production-ready models that drive operational efficiency and measurable business outcomes. As part of the CoE, you'll also have the opportunity to explore intersections with Generative AI and agentic systems, expanding your impact across the full AI spectrum.

Responsibilities

• Design and develop time series forecasting models — using techniques such as ARIMA, Prophet, or gradient boosting — to support demand prediction, trend analysis, and business planning
• Build end-to-end ML pipelines for tabular data, covering data ingestion, feature engineering, model training, validation, and production deployment on cloud platforms
• Collaborate with business stakeholders and domain experts to translate operational challenges into scalable ML solutions for forecasting, scheduling, and optimization use cases
• Develop mathematical optimization and dynamic scheduling solutions using frameworks such as OR-Tools or PuLP to automate complex resource allocation and planning problems
• Apply statistical analysis and predictive modelling techniques to uncover patterns in structured and time-dependent data, generating actionable insights for decision-makers
• Establish and maintain model monitoring, retraining pipelines, and performance evaluation frameworks to ensure ongoing reliability in production
• Document methodologies, model performance, and findings, communicating results clearly to both technical teams and non-technical stakeholders

Requirements

• Advanced Python proficiency with hands-on experience in scikit-learn, XGBoost, LightGBM, statsmodels, and Prophet for tabular and time series modelling
• Strong knowledge of time series forecasting techniques
• Solid experience with mathematical optimization and dynamic scheduling frameworks such as OR-Tools or PuLP
• Strong statistical foundation, with practical knowledge of hypothesis testing, regression analysis, and causal inference methods
• Proven ability to work with structured and tabular data, including advanced feature engineering, preprocessing, and handling of temporal dependencies
• Hands-on experience deploying ML models to cloud platforms (AWS, GCP, or Azure) and maintaining production-ready pipelines
• Master's or Ph.D. degree in Computer Science, Mathematics, Statistics, Operations Research, or a related field
• Strong analytical and communication skills, with the ability to present complex findings clearly to non-technical stakeholders
• Upper-intermediate or higher proficiency in English, both spoken and written