Design, implement, and optimize advanced data processing workflows on large-scale datasets using Python, with a strong emphasis on data-wrangling libraries (such as pandas and numpy) and geo-analytics libraries (such as geopandas and shapely);
Lead the identification, acquisition, validation, and integration of raw datasets to enhance model performance and business insights;
Develop, deploy, and continuously refine predictive models and machine learning algorithms to support travel demand forecasting and strategic decision-making;
Define, calibrate, and optimize key parameters for demand forecasting systems, ensuring model robustness and accuracy;
Support the modeling team in the setup, execution, and analysis of simulations across multiple demand and service scenarios, integrating geo-spatial analytics into the workflow and producing high-quality outputs for GIS-based decision-support tools;
Lead scenario modeling and sensitivity analyses to assess the impact of different mobility policies and service configurations on transit demand;
Collaborate on the development and enhancement of public transport network design and scheduling optimization models (including timetabling solutions);
Conduct advanced exploratory data analysis and develop impactful visualizations and dashboards using tools such as Tableau and Python visualization libraries (e.g., Plotly, Seaborn, Matplotlib);
Act as a data science advisor to cross-functional teams, translating business needs into analytical solutions and ensuring data-driven decision support.
Tələblər
Advanced proficiency in Python programming (or C/C++), with deep knowledge of Python data manipulation libraries (pandas, geopandas) and scientific computing and machine learning libraries (such as Scikit-learn, SciPy, LightGBM, and XGBoost);
Demonstrated practical experience in data cleansing, transformation, advanced analytics, and data visualization, using tools such as Tableau or Python-based visualization frameworks;
Strong expertise in statistical methods and quantitative problem-solving, with practical experience in developing demand forecasting models using techniques such as regression analysis, discrete choice modeling, and advanced curve fitting on real-world datasets;
Solid experience in network design and scheduling optimization, with practical application of network flow models, linear programming (LP), and mixed-integer programming (MIP) methodologies;
Good understanding of parallel and distributed computing principles for handling large-scale data processing and model training tasks;
Hands-on experience with geo-spatial analytics, GIS tools, and familiarity with transport demand modeling and simulation software (e.g., PTV Visum, Aimsun) is considered a strong advantage;
In-depth knowledge of the transportation and mobility industry, with the ability to translate complex business and operational challenges into data-driven analytical solutions;
Excellent communication and collaboration skills, with the ability to work effectively in cross-functional and multidisciplinary teams;
Fluency in English is mandatory; proficiency in Russian is considered an asset;
Advanced Degree (Master's or Ph.D. preferred) in quantitative science such as Data Science, Statistics, Operations Research, Computer Science, or Industrial Engineering;
At least 3–5 years of hands-on experience in data science, advanced data analytics, or predictive modeling, preferably applied to transportation, mobility, or network optimization domains.