Kempuri Data Science team focuses on transforming the largest organizations on the market using machine learning and advanced analytics. Projects involve building predictive and prescriptive engines (Causal ML), as well as automation using GenAI. Example projects includes: risk modeling, propensity/uplift analysis, churn forecasting, and demand forecasting. We are looking for individuals who have strong Python programming skills and the ability to communicate business conclusions, identify business needs, and then translate them into quantitative language.

Work is usually done in iterations that allow for quick and effective assessment of work results and their impact on the business process. Results are either integrated with dedicated applications or incorporated to data orchestration.

Competitive salary package, reflective of experience and qualifications
Opportunity to work remotely, supporting work-life balance
Comprehensive benefits, including health insurance and a sports membership card
Exposure to cutting-edge credit risk modelling technologies and regulatory frameworks
Collaborative environment that encourages knowledge sharing and innovation
Working on comprehensive implementations of models and analyses using ML across the full life cycle: Evangelization, Use Case Hunting, PoC, MVP, Productionization, Industrialization, Maintenance.
Defining the analytical paradigm: how to translate model output into business decisions. Contributing not only to modelling but also results consumption by business / end users.
Analysis and interpretation of model results, goodness of fit, and monitoring.
Consulting on analytical use cases and their business impact.
Preparing conclusions and simulations regarding the impact of ML use cases on business processes: estimating ROI, Uplift, Success Criteria.

Role-specific

Substantive knowledge of Machine Learning concepts.
Commercial experience in building ML solutions using tree-based models (DT, RF, Boosting), generalized linear models (SVM, NN, Regressions, Boosting), distance-based models (KNN), and unsupervised learning.
Experience in gathering business requirements, translating them into an analytical process, defining quality metrics, and a testing process on both historical and new data.
Knowledge of basic and advanced Feature Engineering concepts, data leakage prevention, and ensemble learning.
Python programming skills and experience in building operational ML pipelines in selected environment: Azure Machine Laerning / VertexAI / Sagemaker or similar
Knowledge of DS/ML analytical libraries: Pandas, Scikit-learn, XGBoost / LightGBM, Seaborn, Statsmodels, Keras.
Minimum 4 years of experience in Data Science / ML.

Team

Projects are carried out in teams of 3 to 10 people with various competencies: Data Scientist, Data Engineer, Business Analyst, Architect.