Applied Bioinformatics Engineer, Pipelines & AI

Pipeline Development and Engineering

• Support computational biology workflows, including single cell, spatial, and other multi-omics analysis workflows for clinical and preclinical applications
• Use modern workflow managers (e.g. Nextflow, Snakemake, or similar) and containerization (Docker, Singularity) to make pipelines portable, testable, and reusable across projects and teams
• Help build and maintain reproducible analytical pipelines for statistical genetics and bioinformatics workflows
• Wrap and harden ad-hoc analytical scripts written by scientists into production-quality tools that can be re-run reliably by others
• Write tests, documentation, and clear examples so the pipelines you build are usable by colleagues with a range of technical backgrounds
• Prototype agentic workflows that automate established and routine analytical tasks
• Build and maintain MCP connectors that expose internal data, public resources, and analytical pipelines to LLM-based agents and tools like Claude
• Identify and develop use cases where LLMs and agentic AI workflows can improve the speed, quality, consistency, or accessibility of work across therapeutic areas, focusing on end-to-end capabilities rather than isolated task completion
• Contribute to a shared library of reusable AI tooling, prompt patterns, and integration code that the team can build on
• Define technical standards for evaluation, documentation, guardrails, and workflow quality so that AI-based solutions are trusted, reproducible, and suitable for repeated use across teams and projects
• Stay up-to-date with the latest AI tooling landscape and bring back ideas the team can put to work
• Help improve AI fluency among collaborators by demonstrating practical workflows

Collaboration Across Lilly Research Labs

• Partner closely with statistical geneticists, computational biologists, and software engineers within the Cardiometabolic Data Science group and across other Lilly Research Labs teams
• Work with therapeutic area partners to understand their analytical needs and translate them into pipeline requirements
• Cook with platform and engineering groups to ensure your pipelines integrate cleanly with broader Lilly infrastructure
• Contribute to internal knowledge sharing — code reviews, demos, documentation, and helping colleagues get unblocked

Basic Requirements

• B.S. in computer science, computational biology, bioinformatics, biological sciences, statistics, or a related field, with 10+ years relevant work experience, OR
• M.S. in computer science, computational biology, bioinformatics, biological sciences, statistics, or a related field, with 7+ years relevant work experience, OR
• Ph.D. in computer science, computational biology, bioinformatics, biological sciences, statistics, or a related field, with 1+ years relevant work experience.

Additional Skills/Preferences

• Strong programming skills in Python and/or R including comfort with version control (Git), code review, testing, and writing maintainable code
• Demonstrated experience building data analysis pipelines, ideally using a workflow manager such as Nextflow, Snakemake, or WDL
• Working familiarity with bioinformatics file formats (VCF, BED, GTF, BAM, etc.) and standard tools (PLINK, samtools, bcftools, or similar)
• Familiarity with typical data types in high-throughput biology, including NGS data
• Hands-on experience or strong demonstrated interest in modern AI tooling — using LLMs through APIs, building MCP servers/connectors, prompt engineering, or wiring up agentic workflows
• Demonstrated ability to build stable and practical, reusable workflows and not just code for one-off analyses, with strong implementation skills in Python and modern AI/ML tooling
• A collaborative, low-ego mentality; you enjoy building tools that other people use and you take feedback well
• Comfort with cloud computing environments (AWS, GCP, or Azure) and Linux/command-line work
• Ability to work successfully in a matrixed environment
• Prior experience with statistical workflows/biomedical statistics
• Prior exposure to statistical genetics methods (GWAS, fine-mapping, MR, colocalization, burden testing) or large-scale genomic datasets (UK Biobank, gnomAD, GTEx, Open Targets)
• Prior experience with complex high-throughput biological data or experiments such as spatial transcriptomics, large-scale screens, or multi-omics studies
• Familiarity with R in addition to Python, particularly for statistical genetics packages
• Experience with relational and/or graph databases, and with biomedical ontologies
• Contributions to open-source projects or a public portfolio (GitHub, blog posts, demos)
• Prior experience in pharma, biotech, or academic genomics research