Data Scientist II

What will you get to do here? Design, develop, and deploy scalable optimization algorithms for supply chain, assortment planning etc. Translate business problems into mathematical formulations using tools like Linear Programming, Integer Programming, and Heuristics. Build and improve predictive models using ML techniques (regression, classification, time-series forecasting). Collaborate closely with Product, Engineering, and Operations teams to take models from prototype to production. Analyze model performance and continuously iterate to improve accuracy and efficiency. Drive measurable impact on key business metrics such as availability, wastage, revenue per order, cost per order etcWork on high-impact, real-world problems at massive scale. Be a part of a fast-growing vertical within Swiggy with opportunities to innovate and experiment. Collaborate with a world-class team of engineers, product managers, and data scientists. Competitive compensation and a culture that promotes learning, ownership, and growth. What qualities are we looking for? 3–5 years of experience in Data Science or Applied Research roles. Strong foundation in Operations Research and Mathematical Optimization (e.g., LP, MILP, ILP). Solid hands-on experience with Python, SQL, and at least one optimization solver (e.g., Gurobi, OR-Tools, CPLEX). Good understanding of Machine Learning concepts and frameworks (e.g., scikit-learn, XGBoost, TensorFlow, PyTorch). Experience in solving large-scale real-world problems using a combination of ML and OR techniques. Strong problem-solving skills and ability to work in a fast-paced, collaborative environment. Excellent communication and stakeholder management skills. Experience in supply chain, logistics, food delivery, or q-commerce/e-commerce domains. Prior experience in building real-time or near real-time decision systems. Experience working with large datasets and distributed systems (e.g., Spark). Few requirements I would like to add : Strong understanding of statistical techniques. Distributions and loss functions.  Production level coding standards and not just POC. Understanding of cache layers, database schema designs, abstractions and modularity Experience designing or working with agentic/autonomous decision systems that incorporate human-in-the-loop review, exception handling, or override mechanisms. 3–5 years of experience in Data Science or Applied Research roles. Strong foundation in Operations Research and Mathematical Optimization (e.g., LP, MILP, ILP). Solid hands-on experience with Python, SQL, and at least one optimization solver (e.g., Gurobi, OR-Tools, CPLEX)