In Retail we are building one of the worlds most ambitious applied AI and data science ecosystems, at a scale rarely seen globally. With 1,000+ cities, 18,000+ stores, millions of daily transactions, and a rapidly growing digital commerce footprint, the problems we solve sit at the intersection of machine learning, artificial intelligence, optimization, and real-world operations.

As a Data Scientist at Retail, you will work on high-impact, applied data science problems across online and offline commerce across a broad and evolving set of problem spaces. These are organized into the following thematic clusters (you may specialize in one or rotate across multiple) :

1. Customer, Growth & Commerce Intelligence :

- Search, ranking, recommendations, and personalization

- Customer profiling, segmentation, LTV, churn, and loyalty

- Acquisition, engagement, retention, and lifecycle optimization

- Marketing effectiveness, attribution, uplift, and experimentation

2. Monetization, Pricing & Promotions :

- Dynamic pricing and markdown optimization

- Promotion effectiveness and offer personalization

- Ads relevance, bidding intelligence, and measurement

- Margin optimization and revenue intelligence

3. Supply Chain, Planning & Availability :

- Demand planning and forecasting at scale

- Inventory, replenishment, and allocation optimization

- Network planning, S&OP, and fulfillment intelligence

- Availability, selection depth, and service-level optimization

4. Store, Operations & Physical Retail Intelligence :

- Store efficiency, labor optimization, and compliance

- Planogram intelligence and assortment effectiveness

- Computer vision, video, and sensor-based intelligence

- Shrinkage, fraud, and loss prevention

5. Platform, Automation & Next-Gen AI :

- Intelligent decision engines embedded into workflows

- Agentic systems for automated planning, execution, and monitoring

- Causal, simulation, and digital twin-based modeling

- Reusable ML platforms, feature stores, and inference systems

Why to Apply :

- Work on some of the largest and most complex retail data science problems globally

- Opportunity to influence both digital and physical commerce at massive scale

- Exposure to cutting-edge applied AI, including agentic systems and automation

- Collaborate with industry leaders who have built and scaled pioneering e-commerce and quick-commerce data science organizations

- Build systems that move beyond insightsinto intelligence, autonomy, and action

Key Responsibilities :

- Own end-to-end data science problem solving : from problem framing and data exploration to model development, deployment, and continuous improvement.

- Demonstrate AI-native ways of working through SOTA AI tools like Claude Code, Codex.

- Design and build machine learning, optimization, and AI systems that operate reliably at large scale in production.

- Apply a wide range of techniquesstatistical modeling, ML, deep learning, generative and agentic AI, experimentation, and simulationbased on problem context rather than trend.

- Contribute to shared platforms, reusable frameworks, and best practices that elevate data science maturity across the organization.

- Ensure solutions are robust, explainable, monitored, and governable in real-world environments.

- Communicate insights, trade-offs, and outcomes clearly to technical and non-technical stakeholders.

- Stay current with emerging advances in AI, ML, and agentic systems, and thoughtfully translate them into practical applications.

- Partner closely with product, engineering, and business teams to embed intelligence into decision-making and customer-facing systems.

Functional Competencies :

- ML frameworks : PyTorch, TensorFlow, XGBoost, LightGBM

- Representation learning : embeddings, deep learning, NLP, multimodal models

- MLOps & platforms : feature stores, model registries, CI/CD for ML, monitoring

- Large-scale data processing : Spark, distributed computing, cloud-native stacks

- Working familiarity with LLMs, RAG pipelines, agents, and AI orchestration frameworks

- Visualization and storytelling using modern BI or notebook-driven approaches