Data Scientist (Fulltime or Contract)

Job Overview:

We are looking for an experienced Data Scientist to join our team and develop advanced analytics, machine learning, forecasting, anomaly detection, entity resolution, and data intelligence solutions for an enterprise data platform. The ideal candidate will have strong hands-on experience in statistical analysis, machine learning, Python, SQL, data profiling, predictive modelling, and business problem solving.
The role will focus on improving data quality, standardizing business entities, building forecasting models, identifying anomalies, and generating actionable insights for business teams.

Key Responsibilities:

• Analyze large-scale business datasets, including POS, sales, customer, distributor, product, territory, finance, and operational data.
• Perform detailed data profiling to identify missing values, duplicates, outliers, inconsistent formats, grain differences, and data quality gaps.
• Develop machine learning models for entity resolution, customer/product/distributor matching, data imputation, anomaly detection, segmentation, and forecasting.
• Design and implement POS file similarity cohorting models to group similar file structures and support reusable ingestion/mapping templates.
• Build Named Entity Resolution solutions to standardize customer, distributor, product, territory, and channel names against master data.
• Develop field-level data imputation strategies using rule-based, statistical, and ML-based methods.
• Create data quality scoring frameworks, dataset health scores, and business readiness metrics.
• Build sales forecasting, demand forecasting, and sales landing/projection models using statistical, machine learning, and ensemble techniques.
• Develop anomaly detection models to identify unusual movements in sales, quantity, revenue, unit price, distributor performance, and forecast variance.
• Perform customer and distributor segmentation using RFM, clustering, growth-value analysis, and opportunity scoring.
• Evaluate third-party datasets for business relevance, coverage, joinability, quality, and forecasting value.
• Collaborate with business stakeholders to understand KPI definitions, business rules, reporting requirements, and analytical use cases.
• Work with data engineers to convert model requirements into scalable data pipelines and production-ready feature datasets.
• Work with ML engineers to transition models from experimentation to production deployment.
• Define model evaluation metrics such as precision, recall, F1-score, MAPE, WAPE, RMSE, bias, accuracy, and business impact measures.
• Develop clear model documentation, methodology notes, assumptions, limitations, and business interpretation.
• Support ontology, semantic layer, and NLQ initiatives by helping define business entities, relationships, metrics, and data rules.
• Create dashboards, reports, and analytical summaries to communicate findings to technical and non-technical stakeholders.
• Continuously monitor model performance, data drift, feature drift, and business metric changes.

Qualifications & Skills:

• 5+ years of experience in data science, machine learning, advanced analytics, or statistical modelling.
• Strong hands-on experience with Python, pandas, NumPy, scikit-learn, SciPy, stats models, and Jupyter notebooks.
• Strong SQL skills for data extraction, transformation, validation, and analytical querying.
• Experience in exploratory data analysis, statistical profiling, data quality assessment, and data cleansing.
• Hands-on experience with supervised and unsupervised machine learning models such as Logistic Regression, Random Forest, XGBoost, LightGBM, CatBoost, K-Means, DBSCAN, and Isolation Forest.
• Experience with forecasting models such as moving average, exponential smoothing, ARIMA/SARIMA, Prophet-style models, XGBoost/LightGBM forecasting, and ensemble forecasting.
• Experience with entity matching techniques such as fuzzy matching, token similarity, embeddings, pairwise classification, and confidence scoring.
• Experience with anomaly detection, outlier detection, segmentation, and pattern recognition.
• Strong understanding of feature engineering, model selection, cross-validation, hyperparameter tuning, and model evaluation.
• Experience working with business datasets such as POS, sales, finance, customer master, product master, distributor data, CRM data, or supply chain data.
• Good understanding of data warehousing concepts, dimensional models, fact/dimension tables, and Bronze/Silver/Gold data layers.
• Experience with visualization and reporting tools such as Power BI, Tableau, matplotlib, Plotly, or similar tools.
• Ability to translate business problems into data science use cases and measurable analytical outcomes.
• Strong communication skills with the ability to explain technical concepts, model outputs, and insights to business stakeholders.
• Experience working in Agile delivery teams with data engineers, architects, ML engineers, BI developers, and product owners.

Preferred Qualifications:

• Experience with Azure Databricks, Apache Spark, MLflow, Azure Machine Learning, or similar cloud-based data science platforms.
• Experience with master data management, customer/product matching, entity resolution, or record linkage.
• Experience in sales forecasting, demand planning, financial forecasting, or commercial analytics.
• Experience with data quality frameworks such as Great Expectations, Soda, Deequ, or custom validation frameworks.
• Experience supporting GenAI, RAG, NLQ, semantic layer, or business ontology initiatives is a plus.
• Experience with human-in-the-loop model improvement, active learning, and feedback-based retraining
• Knowledge of MLOps concepts such as model registry, model monitoring, drift detection, retraining, and production scoring pipelines.
• Cloud or data science certifications such as Azure Data Scientist Associate, Databricks Machine Learning Associate/Professional, or relevant ML certification are desirable.