Senior Scientist, Bioinformatics / Computational Biology

Accountabilities

• Design, implement, and deliver robust analyses across genomics, bulk and single-cell transcriptomics, and multi-omics to answer program-critical questions with statistical rigor.
• Assemble genomes, call variants, and perform comparative genomics and phylogenetic analyses on bacterial and viral pathogens to inform antigen selection and surveillance strategy.
• Apply machine learning and statistical modeling to discover biomarkers, stratify patients, predict antigen immunogenicity, and forecast treatment response, translating model outputs into actionable program recommendations.
• Build, optimize, and maintain reproducible workflows using HPC schedulers and AWS to scale analyses, reduce turnaround time, and ensure traceability.
• Design and integrate LLM-powered agentic workflows for literature mining, data extraction, and pipeline orchestration to accelerate discovery and improve developer productivity.
• Work closely with experimental scientists to propose computationally informed experiments, interpret results, and refine study designs to improve confidence and reduce cycle time.
• Generate translational insights through differential expression, pathway enrichment, and functional annotation, connecting molecular signals to biological mechanisms and clinical hypotheses.
• Produce publication-quality visualizations and reports, present findings clearly to cross-functional stakeholders, and champion version control, workflow managers, and reproducible research practices.
• Stay current with emerging tools in bioinformatics, AI/ML, and agentic AI, piloting new approaches, sharing learnings, and scaling successful methods across the portfolio.

Essential Skills and Experience

• PhD in Bioinformatics, Computational Biology, Genomics, Molecular Biology, Computer Science, or a closely related quantitative discipline, with 2–5 years of industry experience.
• Alternatively, MS in a relevant discipline with 4–6 years of industry experience in bioinformatics, computational biology, or genomics.
• Demonstrated track record of independent research through publications, conference presentations, or successful project delivery.
• Proficiency in R and/or Python for genomic data analysis, statistical computing, and data visualization, including tools such as ggplot2, Bioconductor, tidyverse, pandas, and scikit-learn.
• Hands-on experience with NGS data analysis, including alignment tools such as STAR, BWA, and Bowtie2; quantification tools such as Salmon, featureCounts, and HTSeq; and variant calling tools such as GATK and bcftools.
• Familiarity with RNA-seq analysis workflows, including differential expression methods such as DESeq2, edgeR, and limma, as well as pathway analysis and gene set enrichment approaches such as ssGSEA and MSigDB.
• Experience working in Linux/Unix environments and with HPC job schedulers such as SLURM, SGE, or PBS, and/or cloud computing platforms such as AWS or GCP.
• Working knowledge of Git/GitHub and reproducible research practices, including Nextflow or similar workflow managers.
• Solid understanding of molecular biology fundamentals, genome annotation, and public bioinformatics databases such as NCBI, Ensembl, UniProt, and PDB.
• Foundational knowledge of machine learning concepts and applied statistics relevant to biomarker discovery and genomic data.
• Strong analytical thinking, creative problem-solving, and the ability to translate complex datasets into actionable biological insights.
• Excellent written and verbal communication skills, a collaborative mindset, intellectual curiosity, and the ability to manage multiple priorities and deliver results within timelines.

Desirable Skills and Experience

• Experience in at least one therapeutic area—infectious diseases, oncology, or inflammatory disease.
• Experience with comparative genomics and microbial or viral genome analysis, including pangenome methods, AMR gene detection, and phylogenetics.
• Building predictive and prognostic models using supervised and unsupervised machine learning methods on clinical or preclinical omics data.
• Familiarity with deep learning frameworks such as PyTorch and TensorFlow.
• Exposure to biological foundation models such as ESM, EvolutionaryScale, scGPT, TranscriptFormer, and Evo.
• Experience with or strong interest in agentic AI workflows for bioinformatics, including LLM-orchestrated pipelines, retrieval-augmented generation (RAG) for scientific literature, and tool-using AI agents.
• Proficiency with AI-assisted coding tools such as Claude Code or GitHub Copilot.
• Exposure to single-cell RNA-seq tools such as Seurat, Scanpy, and CellRanger.
• Knowledge of structural biology tools, protein modeling, or antigen/antibody design.
• Experience with containerization and infrastructure-as-code.
• Familiarity with LLM APIs and prompt engineering for scientific applications, including structured output generation and multi-agent system design.