Principal Data Scientist

About the Role

We are looking for a Lead/Principal Data Scientist - Forecasting & Decision Science with 7+ years of experience in building scalable, business-impacting data science solutions across predictive analytics, time series forecasting, machine learning, and applied AI.

This role is ideal for someone who is strong in Python, forecasting, advanced analytics, and enterprise-grade model development, and can translate complex business problems into practical, production-ready solutions. The candidate should be comfortable working across the full lifecycle of a data science solution - from problem framing and exploratory analysis to model development, deployment support, business validation, and continuous improvement.

A strong background in forecasting and predictive analytics is essential. Exposure to supply chain / operations use cases, decision science, or agentic AI systems will be an added advantage.

What You’ll Do

• Build and deliver predictive analytics and forecasting solutions for business-critical use cases
• Develop robust models for:
  • Demand Forecasting
  • Sales Forecasting
  • Inventory Analytics
  • Supply / Operations Planning
  • Business Performance Forecasting
• Work extensively with time series and sequential data, including trend / seasonality modeling, lag and rolling features, forecast validation, backtesting, and performance improvement
• Design and implement machine learning models for structured and semi-structured business data
• Perform exploratory data analysis, feature engineering, model evaluation, and hypothesis-driven analysis
• Translate business problems into analytical frameworks, model approaches, features / assumptions, and success metrics
• Build clean, modular, production-friendly Python solutions
• Work closely with business, product, engineering, and data teams to ensure solutions are practical, scalable, and business-aligned
• Support deployment and integration of models into enterprise applications / APIs
• Mentor junior team members and contribute to solution reviews, model quality, and best practices

Must Have

• 7+ years of relevant experience in Data Science, Machine Learning, Predictive Analytics, or Applied AI
• Strong proficiency in Python for data analysis, model development, and solution engineering
• Strong hands-on experience in:
  • Predictive Analytics
  • Time Series Forecasting / Time Series Modeling
  • Machine Learning model development
  • Statistical analysis and feature engineering
  • Regression / classification / forecasting use cases
• Strong understanding of time series and sequential data, including:
  • Trend / seasonality analysis
  • Lag features / rolling features
  • Forecast validation
  • Backtesting
  • Forecast error analysis and performance tuning
• Strong hands-on experience in time series forecasting, predictive analytics, and machine learning, with proficiency in relevant Python-based libraries, frameworks, and model development workflows
• Strong understanding of core data science concepts such as:
  • Supervised / unsupervised learning
  • Model validation and error analysis
  • Feature selection / importance
  • Bias-variance trade-offs
  • Experimentation and hypothesis-driven analysis
• Good understanding of SQL and working with large, structured datasets
• Experience building clean, modular, and production-friendly code
• Strong problem-solving and analytical thinking skills
• Ability to independently convert business problems into:
  • Analytical frameworks
  • Model approaches
  • Features / assumptions
  • Metrics and success criteria
• Strong stakeholder management and business communication skills, with the ability to work closely with business, product, and engineering teams to understand requirements, align on solution approach, and clearly communicate model outputs, assumptions, and recommendations
• Ability to manage ambiguity, drive discussions with cross-functional stakeholders, and translate business asks into structured analytical solutions
• Basic understanding of:
  • Docker / containers
  • Packaging and deployment of Python services / models
  • Linux / command-line basics
  • API integration concepts
• Ability to mentor junior data scientists and review their approach / outputs

Good to Have

• Experience in supply chain / operations domain, especially in one or more of:
  • Demand Forecasting
  • Inventory Analytics
  • Supply Planning
  • Production / Operations Analytics
  • Logistics / Distribution Analytics
• Exposure to optimization / decision-support systems (not mandatory, but beneficial)
• Familiarity with:
  • FastAPI / Flask
  • Git / version control
  • MLflow / experiment tracking
  • Airflow / workflow orchestration
• Exposure to cloud environments such as AWS / Azure / GCP
• Understanding of MLOps concepts such as:
  • Model packaging
  • Deployment workflows
  • Monitoring / retraining pipelines
• Exposure to LLMs / Generative AI / Agentic Systems, including concepts such as:
  • Prompt engineering
  • RAG / context-aware AI systems
  • Tool calling / orchestration
  • Multi-agent workflows
• AI-assisted analytics / decision support
• Experience working on enterprise-scale analytics or decision intelligence platforms