Senior Data Scientist

Valuelabs; Mumbai, Navi Mumbai; On-site; INR 1,500,000 - 3,000,000; Full time

Job summary

Valuelabs is seeking a Data Scientist in Mumbai to lead end-to-end analytics initiatives. You will explore data, engineer features, and build machine learning models for customer segmentation, propensity scoring, and a Next Best Action engine.

Responsibilities include NLP from transcripts, prompts for LLMs, and presenting model performance to stakeholders. A strong foundation in statistics, ML, and data manipulation is required.

Qualifications

• Strong foundation in statistical modeling and ML with hands-on experience.
• Proficiency in Python and data manipulation for model development.
• Experience in customer segmentation, propensity modeling, and NLP is preferred.

Responsibilities

• Develop end-to-end ML models from data exploration to deployment.
• Build segmentation and propensity models; design NBA decision logic.
• Implement NLP modules to extract insights from transcripts and support prompts.

Skills

Statistical modeling

Machine learning

Data manipulation

NLP

Call insights

Customer segmentation

Propensity modeling

NBA engine

Education

Bachelor's degree in a quantitative field

Tools

Python

SQL

TensorFlow

Scikit-learn

NLP tools

Job description

Job Description:

We are seeking a highly skilled and motivated Data Scientist to join our dynamic team. The successful candidate will play a pivotal role in a strategic project focused on developing a deep understanding of our customers through advanced analytics. You will be responsible for the end-to-end development of machine learning models, from initial data exploration and feature engineering to building customer segmentation, propensity models, and a Next Best Action (NBA) engine. This role requires a strong foundation in statistical modeling, machine learning, and data manipulation to transform complex datasets into actionable business insights.

Roles and Responsibilities:

:Data Assessment & Preparation: Execute data quality assessments to quantify completeness, identify gaps, and recommend remediation actions. Ingest and consolidate priority datasets from the Data Lake and external sources. Model Development & Validation: Develop and transform features to prepare model-ready inputs for segmentation and propensity modeling. Build, train, and optimize customer segmentation models using clustering algorithms. Develop a suite of supervised propensity models to rank products based on customer affinity. Design and implement a Next Best Action (NBA) prioritization logic engine to deliver targeted "nudges." Validate models through backtesting, correlation analysis, and business sense checks to confirm stability and relevance. NLP & Call Insights: Implement NLP modules to extract keywords and analyze sentiment from call transcripts. Develop and refine prompts for LLMs to generate accurate and consistent cluster labels and persona descriptions. Collaboration & Reporting: Work closely with the AI Engineering team, business stakeholders, and other data scientists to align on project goals and deliverables. Document and present model performance, insights, and validation results to stakeholders for review and feedback.