Role Overview We are looking for a Senior Data Scientist (8-12 Years) to lead the design and deployment of pricing and revenue-management algorithms in a B2B environment. You will own the full model lifecycle — from exploratory analysis and feature engineering through production deployment and ongoing monitoring — and translate complex quantitative findings into clear, actionable recommendations for commercial stakeholders.

What You’ll Do

- Build and maintain pricing models including price elasticity estimation, customer and product segmentation, quote/contract pricing, and price-realization analytics.
- Design and execute rigorous experiments (A/B tests, CUPED, diff-in-diff, uplift modeling) to measure the impact of pricing interventions.
- Deploy models to production on cloud data platforms (Microsoft Fabric, Snowflake) and monitor performance over time.
- Author dbt transformations and maintain clean, well-tested data pipelines.
- Collaborate with commercial, finance, and product teams to turn model outputs into dashboards, memos, and decision-ready narratives.
- Champion ML-engineering best practices: experiment tracking, model registry, CI/CD, and code review.

Required Skills & Qualifications Core Technical Skills

- Programming: Python and R for statistical analysis and model development.
- Databases: Oracle SQL and ANSI SQL; comfortable writing complex analytical queries from scratch.
- Data Modeling:



experience designing schemas and thinking about data at scale.
- Version Control: Git as part of a daily workflow; familiarity with GitHub/GitLab or Azure DevOps.

Domain Expertise
- Meaningful ownership of pricing or revenue-management algorithms in B2B commercial contexts.
- Hands-on experience with price elasticity modeling, segmentation, and quote/contract pricing analytics.
- Solid grounding in experiment design and statistical inference.

Cloud & DevOps
- Production model deployment on Microsoft Fabric (Lakehouse / Synapse) or Snowflake.
- dbt for data transformations.
- CI/CD practices — GitHub Actions, Azure DevOps pipelines, automated testing.

NICE TO HAVE
- Power BI (or equivalent BI tool) for self-serve dashboard development.
- MLOps exposure: feature stores, model registries (e.g., MLflow), real-time and batch serving patterns.
- Big data: Spark via Microsoft Fabric Lakehouse/Synapse or Snowpark; orchestration with Airflow or Fabric Pipelines.
- Containerization with Docker.

We are an equal chance employer committed to fair and ethical hiring practices. We do not charge any fees or accept any form of payment from candidates at any stage of the recruitment process. If anyone claims to offer employment opportunities in our company in exchange for money or any other benefit, please treat it as fraudulent and report it immediately. Python, Oracle SQL, Data Modeling

📌 Senior Data Scientist (Noida)
🏢 Lumen Technologies India
📍 Noida