Genomic AI Scientist – Drug Discovery Data Scientist

Overview

Lead Lilly Bengaluru's genomic AI portfolio, covering genomic language models, multi-omics foundation models, and AI for genetic medicines and target selection, with about 30% leadership and mentoring and about 70% hands-on technical ownership.

What you'll do

• Define and own the genomic AI technical roadmap, setting scientific direction and securing leadership agreement on priorities and sequencing.
• Mentor and develop bioinformaticians, data scientists, and ML engineers across the genomic AI squads through coaching, design and code reviews, and career-growth conversations.
• Drive alignment across genetic medicine scientists, ML engineering teams, and therapeutic-area partners on roadmap sequencing, trade-offs, and shared success criteria.
• Own genomic AI readouts in leadership, portfolio, and governance forums, translating technical progress into clear business and scientific impact.
• Build a culture of scientific rigor and knowledge sharing through technical reviews, demos, and documentation.
• Lead development, fine-tuning, and benchmarking of DNA/RNA foundation models for sequence-to-expression, variant effect, and regulatory genomics prediction, including ChIP-seq binding modeling.
• Lead the use of generative and predictive sequence models for AAV promoter design, including cross-model scoring and ensemble ranking of candidates.
• Direct on- and off-target prediction for genetic medicines across DNA, RNA, protein, and phenotype layers.
• Partner with genetic medicine scientists to turn model output into design recommendations and go/no-go decisions.
• Integrate genomic model output with human genetic evidence (GWAS, fine-mapping, colocalization) to sharpen target selection.
• Set the team's modeling strategy for multi-omics foundation models spanning DNA, RNA, protein, and clinical phenotype.
• Ensure model-based assessments are reproducible, defensible, and candid about what the evidence does and does not support.

What you'll need

• Hands-on experience building deep learning models on DNA/RNA sequence (e.g., sequence-to-expression, variant effect, regulatory genomics).
• Strong Python and PyTorch or JAX/TensorFlow skills.
• Ph.D. in computational biology, bioinformatics, genomics, computer science, machine learning, or a related quantitative field with 5+ years of post-Ph.D. experience applying machine learning to genomic sequence data; or M.S. in a related field with 8+ years of equivalent experience.
• Proven technical leadership: setting direction and driving cross-team standards on genomic deep learning projects.
• Demonstrated record of mentoring scientists or engineers and aligning scientific, engineering, and leadership stakeholders around shared priorities without formal authority.
• Experience presenting technical strategy and outcomes to senior scientific or engineering leadership, translating technical progress into clear business and scientific impact.

Nice to have

• Deep expertise with DNA/RNA foundation models (e.g., Enformer, DNABERT, Nucleotide Transformer, Evo, HyenaDNA) and their fine-tuning or benchmarking.
• Experience with generative sequence design for regulatory elements, promoters, or AAV/gene-therapy vector components.
• Familiarity with ChIP-seq, ATAC-seq, or other functional genomics data, and experience integrating multi-omics data spanning DNA, RNA, protein, and clinical phenotype.
• Experience working with human genetic evidence (e.g., GWAS, fine-mapping, colocalization) and applying it to target selection.
• Experience leading technical steering groups, cross-functional working sessions, or governance reviews.
• Track record of growing junior talent into independent contributors or technical leads.
• Comfort with GPU/HPC environments, large-scale training workflows, and reproducible ML practices such as experiment tracking, version control, and containerized pipelines.
• Peer-reviewed publications or open-source contributions in genomic deep learning or functional genomics.

Details

• Location: Bengaluru, India.
• No formal people-management responsibility; impact is through influence, mentorship, and technical credibility.