Senior Data Scientist, Computational Biology

Amgen; Hyderabad; On-site; INR 2,500,000 - 4,200,000; Full time

Job summary

Amgen seeks an AIN-based Computational Biology Data Scientist to design and implement predictive biomarker models across clinical trial data. The role blends computational biology, statistics, and ML to enable translational insights and multi-omics integration in Amgen's development portfolio.

You will build scalable, interpretable models linking molecular, cellular, and clinical phenotypes to disease stratification and outcomes, contributing to precision medicine and scalable platforms.

Qualifications

• Experience developing statistical or ML models for complex multi-modal biomedical or clinical datasets.
• Proficiency in Python and R for scientific computing and modeling.
• Experience with modern ML/DL libraries and frameworks and understanding their clinical fit.

Responsibilities

• Design and implement predictive and prognostic biomarker models using clinical trial and biomarker data.
• Develop and apply multi-omic integration frameworks across genomics, transcriptomics, proteomics, and clinical data.
• Apply advanced statistical methodologies including longitudinal, survival, and imputation techniques.

Skills

Python

R

ML frameworks

Multi-omics

Education

PhD in Bioinformatics/Computational Biology/Statistics

MS in quantitative field

Tools

PyTorch

TensorFlow

scikit-learn

MOFA

GitHub

Job description

Role Summary

The AIN-based Computational Biology Data Scientist will design, implement, and advance advanced analytical and AI-driven frameworks to enable translational and reverse-translational insights from clinical trial data across Amgen’s global development portfolio. This role sits at the intersection of computational biology, advanced statistics, and modern machine learning, with a strong emphasis on predictive and prognostic biomarker modeling, multi-omic data integration, and next-generation AI-enabled analytical platforms.

The successful candidate will contribute intellectually and technically to Amgen’s precision medicine strategy by developing rigorous, scalable, and scientifically interpretable models that link molecular, cellular, and clinical phenotypes to disease stratification, efficacy, safety, and adverse event outcomes. This role requires demonstrated depth—not familiarity—in applied modeling, multi-omic analytics, and AI systems, with evidence of impact through peer-reviewed publications, production-grade codebases, or verifiable industry experience.

Key Responsibilities

Advanced Modeling & Translational Analytics

• Design and implement predictive and prognostic biomarker models using clinical trial and biomarker data, including response, resistance, disease stratification, and adverse event endpoints.
• Develop and apply multi-omic integration frameworks ("e.g., factor models, MOFA-style latent variable approaches, matrix factorization, graph-based methods") to jointly analyze genomics, transcriptomics, proteomics, epigenomics, imaging, and clinical covariates.
• Apply advanced statistical methodologies relevant to clinical development, including longitudinal and mixed-effects models, survival analysis, missing data and imputation strategies, confounder adjustment, and model interpretability.
• Contribute to study-level and cross-program analyses that inform mechanism of action, patient selection strategies, and development decisions.

Machine Learning, AI & Emerging Capabilities

• Build and evaluate machine learning, deep learning and causal inference models applied to biological and clinical data, with a clear understanding of model assumptions, limitations, and validation in regulated environments.
• Develop or meaningfully contribute to AI-enabled analytical systems, including:
• Foundation and large language model–based approaches ("e.g., GPT-class models") for scientific workflows
• Generative models for representation learning, hypothesis generation, or simulation
• Agentic AI systems (assistive, conversational, automated, predictive, or sentinel) to support analysis, decision-making, or platform capabilities
• Partner with platform and engineering teams to ensure analytical methods are reproducible, scalable, and production-ready.

Scientific Rigor, Collaboration & Communication

• Translate biological and clinical questions into well-defined analytical strategies and clearly articulate modeling choices, assumptions, and uncertainties.
• Collaborate closely with biomarker scientists, clinicians, biostatisticians, and data engineers across global teams and time zones.
• Communicate complex analytical results and their implications effectively through technical documentation, presentations, and cross-functional forums.
• Operate with scientific independence while proactively seeking alignment and clarification in a highly matrixed, global development environment.

Basic Qualifications

• Doctorate degree in Bioinformatics, Computational Biology, Statistics, Mathematics, Computer Science, Data Science, or a related quantitative discipline with 1–2 years of relevant experience OR
• Master’s degree in a quantitative discipline with 5 years of relevant experience
• 6+ years of experience in an industry setting

Preferred Qualifications

Candidates should provide verifiable evidence for most of the following:

Quantitative & Computational Depth

• Demonstrated, hands‑on experience developing statistical or machine learning models for complex, multi‑modal biomedical or clinical datasets, evidenced by:
• Peer-reviewed publications in reputable journals, and/or
• Public or internal GitHub repositories with substantive analytical or modeling contributions, and/or
• Clearly documented industry experience supporting clinical or translational programs.
• Proven expertise in Python and R for scientific computing and modeling, including the development of reusable, well‑documented analytical code.
• Experience with modern ML/DL libraries and frameworks ("e.g., PyTorch, TensorFlow, scikit‑learn, tidymodels"), with an understanding of when such methods are appropriate given clinical context.

Translational & Clinical Relevance

• Demonstrated understanding of drug development and clinical trial data, including biomarker strategies, endpoint definitions, and translational study design.
• Experience working with real‑world clinical or biomarker data, including data QC, preprocessing, feature engineering, integration, modeling, and interpretation.
• Familiarity with common clinical biomarker modalities and data types ("e.g., NGS, transcriptomics, proteomics, imaging, immunoassays").

AI, Innovation & Platform Mindset

• Direct experience applying or extending generative AI, foundation models, or agentic systems for scientific, analytical, or decision‑support use cases.
• Ability to critically evaluate new methods and technologies and assess their suitability for regulated, high‑impact biomedical applications.

Professional & Global Operating Skills

• Excellent written and spoken English communication skills, with the ability to explain complex quantitative work to diverse audiences.
• Experience working with global teams and stakeholders across time zones; willingness to operate flexibly to support global programs.
• Demonstrated intellectual humility, adaptability, curiosity, and the ability to pivot analytical approaches as program needs evolve.
• Strong sense of ownership, scientific judgment, and accountability in complex, interdisciplinary projects.

What Will Distinguish Top Candidates

• Clear evidence of end‑to‑end ownership of analytical work that influenced scientific or development decisions.
• Depth in framework‑building, not just model application.
• A demonstrated ability to balance methodological sophistication with biological and clinical relevance.
• Prior experience in large, global biotech or pharmaceutical organizations is strongly preferred.