Data Science Specialist

Hello everyone

we are looking for data scientist

experience :7 to 8 years

location : remote

As discussed, please find below the new requirement.

Job Title: Data Scientist – Attrition & Retention Analytics

Responsibilities

Job Description

Overview

We're seeking a hands-on Data Scientist contractor to build and productionize attrition risk models and retention insights for HR stakeholders. The ideal candidate has shipped attrition models in real production systems and brings strong technical expertise in survival analysis and causal inference to drive data-informed decision-making.

Key Responsibilities

Model Development & Analytics

• Build attrition prediction and time-to-exit models using survival analysis techniques (Kaplan–Meier, Cox Proportional Hazards; bonus: Accelerated Failure Time models, competing risks frameworks)

• Design and implement causal inference frameworks for evaluating HR interventions (Propensity Score Matching/Weighting, Regression Discontinuity Design; bonus: Difference-in-Differences, causal forests/uplift modeling)

• Translate business questions from HR teams into measurable analytical outcomes (time-to-attrition, hazard ratios, retention lift, intervention ROI)

Production & Deployment

• Productionize end-to-end ML pipelines including feature engineering, model training, deployment, monitoring, and periodic retraining

• Build explainable model outputs and actionable decision playbooks in partnership with HR and People Analytics stakeholders

• Ensure privacy-safe modeling practices with proper PII handling and fairness/bias validation

• Experience in Data Science or Applied Machine Learning with at least one production model deployment

• Proven track record building and shipping attrition or retention models in real-world systems

• Strong expertise in survival analysis: Cox Proportional Hazards (including assumptions/diagnostics, handling censored data; time-varying covariates is a plus)

• Strong expertise in causal inference: Propensity Score Matching/Inverse Probability Weighting, Regression Discontinuity Design, and solid understanding of identification assumptions

• Python proficiency: pandas, numpy, scikit-learn, statistical modeling libraries (statsmodels, lifelines), SQL

• Ability to communicate complex analytical results to non-technical business stakeholders clearly and effectively

• MLOps & Infrastructure: Experience with MLflow, Airflow, Docker, CI/CD pipelines, model monitoring frameworks

• Big Data: Hands-on experience with large-scale data processing using Spark/Databricks

• Industry Experience: Background in Healthcare, Marketing, or Manufacturing industries