Data Scientist (ML / Data Analytics / Database / Azure)

We are looking for a highly experienced Data Scientist to become a long-term member of our team. This is not a standalone research role. You will work closely with Product, Engineering, Data Engineering, Marketing, and Business teams to continuously improve the quality, accuracy, and business value of our data products. Please do NOT apply if you are looking for: 1. A one-time or short-term project. 2. A role where you split your attention across many clients and projects throughout the day. 3. A position focused primarily on completing tasks rather than achieving measurable business results. 4. An independent role with minimal collaboration. This position requires close cooperation with a cross-functional team and active participation in discussions, planning, and continuous improvement. Responsibilities • Design, develop, and continuously improve Machine Learning models. • Analyze millions of records and identify trends, anomalies, and data quality issues. • Build scalable data pipelines for processing, validation, and model execution. • Continuously improve prediction accuracy through feature engineering, model tuning, and data analysis. • Investigate data inconsistencies and determine root causes rather than simply processing input data. • Learn and understand the business domain, retailer structures, products, categories, and customer behavior. • Work with large SQL databases and optimize complex analytical queries. • Implement data validation, quality control, and automated monitoring. • Maintain version history of datasets, models, and delivered analytical results. • Collaborate closely with Data Engineers, Developers, Product Managers, Marketing, and Business stakeholders. • Design AI-driven approaches to automate analytical and validation processes. • Document methodologies, assumptions, and model performance. • Take ownership of analytical solutions from concept through production. Requirements • 5+ years of experience as a Data Scientist or Senior Data Scientist. • Strong expertise in Machine Learning, statistical modeling, and predictive analytics. • Advanced SQL and database design experience. • Strong Python skills (Pandas, NumPy, Scikit-learn, XGBoost/LightGBM or similar). • Experience working with millions of records and large-scale analytical datasets. • Experience designing production data pipelines and automated ML workflows. • Hands-on experience with Microsoft Azure (Data Factory, Storage, SQL, Synapse, Databricks, ML Services, or similar). • Experience applying AI techniques to automate business processes and data analysis. • Strong data validation, cleansing, and anomaly detection skills. • Experience with retailer, e-commerce, pricing, inventory, sales, or marketing analytics is highly preferred. • Ability to optimize model performance and continuously improve business KPIs. • Experience with version control (Git) and reproducible analytical workflows. • Strong analytical thinking and excellent problem-solving skills. • Ability to manage multiple priorities and work on several projects simultaneously. • Excellent communication skills and ability to work within a cross-functional team. • Self-driven, detail-oriented, proactive, and committed to delivering production-quality solutions. Nice to Have • Experience with LLMs and AI Agents. • Knowledge of Power BI or similar BI platforms. • Experience with web scraping or large-scale data collection. • Experience with MLOps, CI/CD, Docker, Kubernetes, or cloud-native deployments. • Experience with Azure DevOps. Additional Responsibilities • Design and implement automated Data Quality (DQ) validation framework to detect missing, inconsistent, duplicate, and anomalous data before it reaches production. • Develop Data Quality dashboards that provide real-time visibility into data health, validation results, model accuracy, pipeline status, and historical trends. • Define KPIs and quality metrics, proactively identify issues, and recommend corrective actions. • Continuously monitor production pipelines and improve data reliability and consistency. Additional Requirements • Experience building automated Data Quality (DQ) frameworks and validation rules. • Experience creating operational dashboards (Power BI or similar) for monitoring data quality, model performance, and pipeline health. • Strong understanding of data governance, validation methodologies, and production monitoring. We are looking for someone who investigates problems deeply, challenges assumptions, continuously improves results, and takes ownership of delivering reliable, scalable, and production-ready analytical solutions. We are open to discussing the final budget with candidates whose experience and skills align with our requirements