Role Overview

This role will work closely with a Senior Data Scientist to support patient finding initiatives across Amgens Rare Disease Business Unit (RDBU). The candidate will contribute to analytics and modeling efforts spanning multiple stages of the patient journey, helping identify patients earlier and enable timely intervention.

Live | What you will do
- Support analytics and predictive modeling projects across commercial data science use cases
- Assist in data preparation, exploratory analysis, feature engineering, and performance tracking
- Contribute to development of predictive models under guidance of senior data scientists
- Support patient finding use cases across the patient journey (e.g., pre-diagnosis signals, diagnosis, treatment triggers, relapse indicators)
- Assist in generating actionable insights and summaries for business stakeholders
- Maintain and operationalize code assets, dashboards, and data pipelines in Python/SQL environments
- Follow best practices for documentation, version control, and reproducibility




- Collaborate with cross-functional teams and participate in stakeholder discussions alongside L5 leads
- Continuously learn and apply methods such as predictive modeling, experimentation, and causal inference

Thrive | What you can expect

As we work to develop treatments that take care of others, we also work to care for our teammates professional and personal growth and well-being.
- Exposure to end-to-end data science delivery in a commercial pharma setting
- Prospect to work on rare disease patient finding and patient journey analytics
- Mentorship from experienced data scientists and exposure to advanced modeling techniques
- A collaborative environment focused on learning, impact, and growth

Basic Qualifications
- Bachelors or Masters in Data Science, Engineering, Statistics, or a related quantitative field
- 3-5 years of experience in analytics, modeling, or data science delivery
- Working knowledge of Python and SQL ; e

📌 Data Scientist (Hyderabad)
🏢 Amgen
📍 Hyderabad