ORMAE is a fast-growing consulting firm specializing in Data Science, Optimization, and GenAI solutions across industries. Founded and led by Amit Garg, who holds a Guinness World Record in Mathematics and a PhD in Operations Research, ORMAE excels in delivering cutting-edge solutions at the intersection of technology and business. We are now looking for a hands-on Senior Data Scientist with 5+ years of experience who can lead projects end to-end - from data exploration to scalable deployment - with strong expertise in forecasting, large-scale analytics and adaptive learning systems.

Key Responsibilities:

- Design and implement advanced forecasting models (statistical, ML, DL) for large scale datasets, including multi-SKU, multi-location, and multi-horizon forecasting.

- Work on complex supply chain datasets, including demand planning, inventory movement, lead times, seasonality, promotions, and external drivers.

- Build and maintain feedback-loop mechanisms with planners (model overrides, adjustments, bias monitoring) to ensure adaptive, continuously learning forecasting systems.

- Develop scalable data processing pipelines using Python and Spark/distributed frameworks to manage millions of records efficiently.

- Build NLP components (classification, extraction, embeddings) for analytics use cases where required.

- Contribute to building and integrating LLM-powered tools (prompting, retrieval, light agent workflows) for automation.

- Deploy and monitor solutions on Azure or AWS, ensuring reproducibility, version control, and observability of model performance.

- Collaborate with Power BI experts to integrate model outputs into reports anddashboards for planners and business stakeholders.

- Contribute to internal accelerators and reusable frameworks for forecasting, MLOps, and cloud-based analytics.

- Communicate analytical findings clearly with cross-functional teams - including operations, consulting, and leadership.

Required Skills:

- Forecasting: ARIMA, ETS, Prophet, ML-based forecasting, hierarchical forecasting, causal models

- Proven experience handling large-scale time series datasets (multi-SKU, multi region, millions of rows).

- Experience building adaptive/continuous learning forecasting systems, including planner overrides, back testing, auto-retraining, and KPIs (MAE/MAPE/Bias).

- Distributed Computing: Spark (PySpark preferred) or equivalent frameworks for scaling pipelines.

- Programming: Python (pandas, numpy, scikit-learn, PyTorch/TensorFlow), SQL

- NLP (Foundational): embeddings, transformers, basic extraction/classification (deep expertise not required)

- LLM Tools: Basic prompt engineering and retrieval-based systems (nice-to-have)

- Deployment: Docker, FastAPI/Streamlit, MLflow (preferred)

- Cloud: Azure or AWS experience (model deployment, storage, CI/CD)

- Strong analytical mindset with the ability to translate real supply chain/business problems into ML solutions

- Comfort working in a lean, fast-paced, high-ownership consulting environment

Good to Have:

- Experience with Power BI or other visualization tools

- Exposure to Ops Research / Optimization problems

- MLOps experience: monitoring, model drift detection, automated retraining