Bioinformatics Scientist

Amgen Technology; Hyderabad; On-site; INR 3,000,000 - 5,000,000; Full time

Job summary

Amgen Technology seeks a Bioinformatics Scientist to design and implement advanced analyses and reproducible pipelines for biomarker discovery and clinical development. You will translate complex genomics and single-cell data into robust results for computational biologists and clinical teams.

The role emphasizes cutting-edge AI/ML approaches, cloud and HPC workflows, and collaboration with biomarker labs and CROs. Strong programming and workflow experience are required.

Qualifications

• Strong advanced programming in Python and R for omics data.
• Experience designing production pipelines for NGS/omics data.
• Background in bioinformatics with reproducible workflows.

Responsibilities

• Design, automate, validate, and execute bioinformatics analyses and pipelines.
• Implement reproducible workflows with Nextflow or Snakemake and Docker.
• Lead scalable multi-omics integration for biomarker discovery and trial data.

Skills

Python

R

NGS/omics

Single-cell

Spatial omics

Data science

AI/ML

Git

CI/CD

Education

Master's or PhD in Bioinformatics/Computational Biology

Tools

Nextflow

Snakemake

Docker

AWS

GPU

Job description

Role summary

We are seeking a strong Bioinformatics Scientist to design, automate, implement, validate, and execute advanced bioinformatics analyses and reproducible pipelines that support biomarker analysis, translational research, and clinical development. This individual contributor role combines deep technical expertise in NGS/omics analyses, scRNA/spatial omics, data science, modern AI technologies and software engineering with strong scientific judgment to translate biological data into robust, reproducible results used by computational biologists, translational scientists, data engineers and clinical teams.

Key responsibilities

• Design, develop, validate, automate and maintain end-to-end bioinformatics analysis pipelines and tools for genomics, transcriptomics, single-cell, spatial omics, proteomics, epigenomics, MRD, metabolomics, and related biomarker assays.
• Implement reproducible workflows using workflow engines (e.g., Nextflow, Snakemake) and containerization (e.g., Docker); ensure provenance, versioning and CI/CD for pipelines.
• Lead the design and optimization of production-grade bioinformatics pipelines and analytical workflows, driving improvements in runtime efficiency, memory footprint, scalability, reproducibility, and cost-effectiveness for large-scale genomic and multi-omics analyses.
• Design and implement scalable multi-omics integration frameworks that combine genomic, transcriptomic, proteomic, imaging, and clinical data to enable biomarker discovery, patient stratification, predictive modeling, and data-driven decision-making in drug development and clinical trials.
• Develop state-of-the art agentic workflows, build agents capable of QC, tool selection, execution optimization, and results interpretation
• Define and execute QC, benchmarking and validation strategies for pipelines and algorithms; perform evaluation and assessment of technical wetlab platforms through data; produce metrics and reports documenting performance and limitations.
• Collaborate with internal biomarker labs and CROs/vendors to onboard new assays; author and maintain data transfer specifications, interface control documents, and acceptance criteria. Ensure cross functional coordination and data integrity.
• Produce high-quality technical documentation, statistical methods descriptions, and contribute methods sections for reports, regulatory submissions and publications.
• Troubleshoot and resolve pipeline issues and collaborate with cross-functional teams to deliver timely results.

Required qualifications

Education experience

• Masters or PhD in Bioinformatics, Computational Biology, Genetics/Genomics, Computer Science, Statistics or a related discipline.
• ~8+ years of relevant hands‑on experience in bioinformatics or computational biology, including experience designing and delivering production or research pipelines for NGS/omics data.

Technical skills

• Strong programming skills in Python and R. Familiarity with other languages (C/C++, Java) is a plus.
• Deep understanding of biomarker assays and sequencing technologies (immunoassay, flow cytometry, immunohistochemistry, proteomics, whole genome sequencing, exome sequencing, targeted panel sequencing, bulk RNA‑seq, methylation, metabolomics)
• Hands‑on experience with NGS analysis workflows (alignment, variant calling, RNA‑seq, single‑cell, fusion detection, copy number, structural variants) and with downstream statistical methods for omics data (pathway annotation, GSVA/GSEA, DE analysis).
• Experience with single cell RNA‑seq and spatial transcriptomics data is a plus.
• Practical experience with workflow engines (Nextflow, Snakemake) and containerization (Docker/Singularity).
• Experience with cloud (AWS) and HPC environments and scalable compute frameworks. Experience using GPU is a plus.
• Solid understanding of data formats and standards (FASTQ, BAM/CRAM, VCF/MAF, HDF5/AnnData/Seurat) and metadata best practices.
• Deep knowledge of public genomics, transcriptomics, proteomics, and clinical databases, including TCGA, GTEx, GEO, SRA, dbGaP, cBioPortal, ClinVar, COSMIC, gnomAD, and UniProt, to support biomarker discovery, genomic interpretation, and translational research.
• Experience and expertise with deep learning models, foundation models, large language models (LLMs), RAG, and agentic AI workflows is preferred.
• Familiarity with version control (Git), CI/CD, automated testing, and reproducible research practices.
• Strong statistical reasoning and experience applying appropriate models and QC for biological data.
• Experience with benchmarking and validation frameworks, unit/integration testing for pipelines.
• Prior experience in a biomedical/pharmaceutical environment