Assitant Manager - Data science

• End-to-End Modeling: Build, train, and deploy machine learning models, including survival and hazard-based models, to estimate sale probabilities and recommend item-level pricing and disposition actions.
• Data Feature Engineering: Assess data readiness, perform feature engineering, and develop meaningful features using demand signals, seasonality, costs, historical trends, and other relevant business variables. Design effective approaches to address data gaps and quality issues.
• Model Validation MLOps: Test models in shadow mode, evaluate real-world performance against established benchmarks, and collaborate with Data Engineering teams to develop scalable MLOps pipelines, including feature stores, CI/CD, model monitoring, and deployment.
• Business Client Partnership: Work closely with clients and business stakeholders to understand complex business requirements and translate business rules into scalable machine learning solutions and modeling roadmaps.
• Leadership Delivery: Act as a technical point of contact for client engagements, drive agile delivery, collaborate with cross-functional teams, and mentor a small team of Data Scientists.

• Python, SQL, PySpark, Machine Learning, Survival Analysis, Hazard Modeling, MLOps, Snowflake, dbt, Tableau, and Team Leadership.
• Strong understanding of statistical modeling, feature engineering, model validation, experimentation, and production ML deployment.
• Experience with Pricing, Inventory, Revenue Optimization, or Lifecycle Management is preferred.
• Knowledge of constrained optimization, decisioning systems, cloud-native ML tooling, model monitoring, feature stores, and CI/CD is an added advantage.

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.