Assistant Manager (Data Science)

Drive strategic business value by leading the end-to-end development and deployment of Machine Learning solutions. The primary focus is to build robust, data-driven decisioning systems that help clients optimize revenue, maximize asset returns, and automate complex lifecycle strategies.

Responsibilities:

End-to-End Modeling: Build and train survival/hazard-based models to estimate sale probabilities and recommend item-level pricing and disposition actions.

Data & Feature Engineering: Evaluate data readiness, engineer complex features (demand signals, seasonality, costs), and design workarounds for data gaps.

MLOps & Deployment: Test models in shadow mode, measure real-world performance against benchmarks, and collaborate with Data Engineering to build scalable MLOps pipelines (feature stores, CI/CD).

Leadership & Strategy: Act as the primary technical point of contact for clients. Translate complex business rules into a modeling roadmap and mentor a small team of data scientists through agile delivery.

Skills:

Python, SQL, PySpark, Machine Learning (Survival/Hazard modeling), MLOps, Snowflake, dbt, Tableau, and Team Leadership.

Pricing/Inventory domain expertise, constrained optimization, and cloud-native ML tooling.