Posted 12 July, 2026
Senior Machine Learning Architect
Supplier Login
Bangalore,Karnataka,India
Full Time
Reference: 365_626339_26-00113
Job Summary: We are looking for Senior ML Architect for a remote contract role to design and deploy a production-grade ML system optimizing store-SKU level model stock distribution across 1,200+ stores and ~300 SKUs. You will operate as a senior individual contributor, translating business goals like reduced stockouts and sales lift into scalable, containerized solutions. The position offers flexible hours in a global timezone (CST-aligned), 40 hours/week from March 2 to June 30, 2026 (120 days), based in India Remote (Bengaluru).
Key Responsibilities:
- Architect end-to-end ML systems for high-dimensional retail demand modeling, incorporating regional, demographic, climate, historical sell-through, promotional, and behavioral signals.
- Build production-grade Python-based ML pipelines with advanced forecasting (hierarchical time-series, gradient boosting, hybrid approaches).
- Design allocation and constrained optimization logic to convert forecasts into actionable model stock targets.
- Validate model performance via backtesting, live pilots, and controlled experiments to prove incremental lift.
- Engineer feature pipelines, deploy containerized solutions, and create repeatable retraining/calibration processes.
- Collaborate cross-functionally to define measurable outputs from ambiguous requirements and document methodologies for executive review.
Key Requirements:
- Experience: 7+ years in applied ML/data science; proven multi-dimensional forecasting (store-SKU/geo-segmented); demand forecasting/inventory optimization/retail analytics; production deployment in containerized environments; whiteboard-to-deployment track record.
- Skills: Deep Python proficiency; modern ML frameworks; handling large structured datasets at scale.
- Preferred: Retail/supply chain domain; hierarchical time-series forecasting; allocation/optimization on forecasts; A/B testing frameworks; consulting/startup experience in ambiguity.
