Senior Data Scientist

Overview

Fanatics

Website: Visit Website

Business Type: Startup

Company Type: Product

Business Model: B2B

Funding Stage: Pre-seed

Industry: E Commerce

Salary Range: ₹ 40-55 Lacs PA

Job Description

We’re looking for a Senior Data Scientist to join our team — a group focused on maximizing both the operational efficiency of our supply chain and the financial performance of our inventory. Our work spans inventory allocation and sourcing, internal transfers, network simulation, as well as product lifecycle modeling, pricing, and promotional optimization. While the immediate focus of this role is on inventory and price optimization, we’re seeking candidates with strong data science fundamentals and a broad appetite. The ideal candidate is excited to work across domains, from operational modeling to forecasting, pricing, and product strategy — bringing a rigorous, ML-driven mindset to each.

Key Responsibilities

• Modeling & Forecasting: Develop and maintain predictive models across supply chain and inventory initiatives — including forecasting models, classification, regression, clustering, and segmentation tasks.
• Optimization & Simulation: Build and refine models for network optimization, inventory allocation, sourcing, and internal transfers — using discrete optimization, simulation, and heuristic/metaheuristic techniques.
• Exploratory Analysis & Feature Development: Use EDA and statistical analysis to develop features, understand drivers of performance, and improve model design.
• Time Series Analysis: Design, test, and deploy time series models for demand forecasting, product performance tracking, and lifecycle modeling.
• Cross-Functional Collaboration: Work closely with engineering, product, and operations partners to frame problems, communicate insights, and translate models into decisions and tools.
• Tooling & Automation: Build scalable pipelines and decision-support tools using Python, Spark, and cloud-based infrastructure.
  
  

• Bachelor’s or Master’s degree in Data Science, Computer Science, Statistics, Operations Research, or a related field
• 5+ years of experience building and deploying models in a production or operational environment
• Proficiency in Python (Pandas, Scikit-learn, NumPy) and SQL; experience with Spark or other distributed frameworks
• Demonstrated experience with supervised learning (regression, classification), unsupervised learning (clustering, dimensionality reduction), and model evaluation techniques
• Strong background in time series forecasting, including both classical (e.g., ARIMA, exponential smoothing) and ML-based methods (e.g., XGBoost, LSTM, DeepAR)
• Experience applying discrete optimization (e.g., MIP, constraint solvers, genetic algorithms) to real-world problems
• Familiarity with simulation-based modeling and tradeoff analysis
• Experience with data visualization tools (e.g., Superset, Tableau) and stakeholder-facing communication
  
  

Strong communication skills, with the ability to explain complex modeling approaches to technical and non-technical audiences