Senior Expert II Data Scientist

Novartis India; Hyderabad; On-site; INR 3,000,000 - 5,500,000; Full time

Job summary

Novartis India is seeking a highly skilled Data Scientist in Modeling & Simulation to advance data-driven drug discovery. You will transform large-scale experimental datasets into scalable digital solutions, and collaborate with IDD and PKS teams across the US and Switzerland.

The role demands a PhD with 7–8 years in drug discovery, strong ML/statistics, Python or R, and experience deploying production-grade data products. You will shape analytical workflows and communicate findings clearly.

Qualifications

• PhD in life sciences or related field with 7–8 years in drug discovery.
• Expertise in ML, statistics, and data science workflows for drug discovery.
• Proficiency in Python and/or R with solid software engineering practices.
• Experience deploying production-grade data products or ML systems.
• Strong data visualization and exploratory analysis skills.
• Excellent communication and ability to translate complex concepts to insights.
• Experience with PK/ADME/PK-PD modeling is preferred.
• Familiarity with modern web/frameworks (e.g., JavaScript, Svelte) is a plus.

Responsibilities

• Design, build, and maintain scalable data pipelines and analytical workflows.
• Develop, deploy, and maintain ML models for structure–property insights.
• Apply statistics and data mining to complex biological and chemical data.
• Write production-quality code with testing and version control.
• Collaborate with cross-functional teams to integrate solutions.
• Communicate findings clearly to diverse stakeholders.

Skills

Machine learning

Statistics

Data science workflows

Communication skills

Data visualization

Exploratory data analysis

Cross-functional collaboration

Education

PhD in life sciences or related field

Tools

Python

R

JavaScript

Svelte

Job description

Summary

Join the Modeling & Simulation Data Science team within the Translational Medicine, Pharmacokinetic Sciences Unit to advance data-driven drug discovery. This role combines advanced data science with robust software engineering to transform large-scale experimental datasets into impactful insights and scalable digital solutions supporting drug discovery and development.

Summary

Join the Modeling & Simulation Data Science team within the Translational Medicine, Pharmacokinetic Sciences Unit to advance data-driven drug discovery. This role combines advanced data science & robust software engineering to transform large-scale experimental datasets into impactful insights and scalable digital solutions supporting drug discovery and development.

We are seeking for a talent to provide support at Biomedical Research India within Pharmacokinetic Sciences (PKS) Modeling & Simulation, focusing on lead identification and optimization in close collaboration with Novartis colleagues in the US and Switzerland, to discover and advance innovative methods addressing areas of high unmet medical need. The PKS department handles a high volume of experimental data across ADME, PK and PD domains. This role plays a critical part in leveraging these data through advanced analytics, machine learning, and software engineering to inform decision-making, accelerate lead optimization, and enhance reproducibility and scalability of scientific workflows.

About The Role

Major accountabilities

• Serve as a trusted partner between Data & Digital (D&D) and PKS wet and dry lab teams to identify gaps and translate business needs into strategically aligned solutions within the D&D portfolio.
• Act as a data science representative in Integrated Drug Discovery (IDD) programs, providing scientific and strategic input using experimental and computational data.
• Design, build, and maintain scalable data pipelines, applications, and analytical workflows.
• Develop, deploy, and maintain machine learning models to uncover structure–property relationships and support decision-making.
• Apply statistical analysis and data mining techniques to derive insights from complex biological and chemical datasets.
• Write production-quality, maintainable code following software engineering best practices (testing, version control, documentation).
• Collaborate across cross-functional teams to integrate computational solutions into scientific workflows.
• Identify opportunities for automation, improved data usage, and development of in silico models and digital tools.
• Communicate findings clearly to diverse audiences and contribute to the adoption of data-driven approaches.

Minimum requirement

• PhD in life sciences, computational biology, cheminformatics, bioinformatics, or a related field, and 3-4 years (PhD) / 7-8 overall years of relevant work experience in drug discovery within biomedical or pharmaceutical research settings.
• Strong expertise in machine learning, statistics, and data science workflows applied to drug discovery.
• Proficiency in Python and/or R with solid software engineering practices.
• Experience designing and deploying production-grade data products or ML systems.
• Strong understanding of data visualization and exploratory analysis.
• Excellent communication skills and ability to translate complex concepts into actionable insights.
• Experience in pharmacokinetics (PK), ADME, or PK/PD modeling.
• Familiarity with modern application frameworks or front-end technologies (e.g., JavaScript, Svelte).
• Experience with advanced ML methods such as deep learning or generative models.
• Experience working with large-scale scientific datasets and data platforms.

Why Novartis

Helping people with disease and their families takes more than innovative science. It takes a community of smart, passionate people like you. Collaborating, supporting and inspiring each other. Combining to achieve breakthroughs that change patients’ lives. Ready to create a brighter future together? https://www.novartis.com/about/strategy/people-and-culture

Benefits and Rewards

Learn about all the ways we’ll help you thrive personally and professionally.

Read our handbook (PDF 30 MB)