Key Responsibilities
- Design and delivery of ML/analytics solutions (forecasting, propensity, segmentation, churn, ranking, personalization) across retail and e-commerce use cases.
- Translate business inputs into clear ML problem statements, data requirements, KPIs, and success metrics.
- Perform deep EDA, identify drivers/opportunities, and communicate insights through strong storytelling tailored to business stakeholders.
- Build robust feature engineering and scalable modeling pipelines (Spark/PySpark preferred).
- Select appropriate model evaluation methods (metrics, validation strategy, leakage prevention, error analysis) and ensure reliability.
- Partner with engineering/platform teams to operationalize models (batch/real-time), including monitoring, drift checks, and retraining strategy.
- Drive technical documentation, code quality, and best practices; contribute to team standards and reviews.
- Hands-on exposure to Computer Vision and Generative AI/LLMs (e.g., RAG, embeddings, prompt engineering, agent workflows) for retail use cases such as product search, customer support, and content understanding.
Required Qualifications
- Bachelor’s/Master’s (or equivalent experience) in Data Science, CS, Statistics, Math, or related field.
- 4-8 years in data science / applied ML / advanced analytics with demonstrated production impact.
- Strong Python (Pandas, NumPy, Scikit-learn) and solid SQL.
- Strong foundations in classical ML, feature engineering, and model evaluation.
- Experience working with large-scale data; exposure to Spark/PySpark and modern data platforms.
- Strong communication and ability to influence decisions with data.
Preferred Qualifications
- Retail/e-commerce experience (demand forecasting, pricing/promo, inventory, conversion, customer lifecycle).
- Exposure to MLOps (CI/CD basics, monitoring, experiment tracking, drift/retraining).
Cloud experience (Azure preferred).
