Bioinformatics Analyst II - # 26-18673

We are seeking a motivated Bioinformatics scientist with expertise at the intersection of artificial intelligence, agentic software development, and computational biology. This individual will be responsible for designing and building an agentic AI framework capable of connecting and reasoning across diverse genetic and functional data types to generate insights into disease mechanisms and therapeutic targets., * Collaborate with genetic experts to develop agentic capabilities that can query, connect, and reason across genetic and genomic datasets to support target identification and disease mechanism hypotheses.

• Document architecture, agent workflows, and server configurations for knowledge transfer and long-term maintainability.
• Develop tool-use pipelines that allow agents to programmatically access public genetic databases and interpret results in biological context.
• Design reproducible, modular code that enables other scientists to extend or adapt agent workflows for new questions.
• Work with geneticists and computational biologists to ensure agent outputs are scientifically grounded and actionable.
• Document workflows and present progress at regular project milestones.

• Working knowledge of foundational genetic concepts such as laws of inheritance, linkage disequilibrium, population stratification, etc.
• Demonstrated project experience building AI agents, including multi-agent orchestration, tool use, memory, and reasoning pipelines.
• Experience connecting agents to external APIs, databases, and structured/unstructured data sources
• Strong Python skills; familiarity with relevant libraries (e.g., Pandas, Biopython, scikit-learn, llm harnesses or similar)
• MS+1 or PhD in the quantitative sciences (Bioinformatics, Computer Science, Computational Genetics, Mathematics, Statistics, or a related field). 3-5 years of experience
• Experience with code reproducibility (e.g. github) and HPC environment, * Experience with genome-wide association studies (GWAS), including fine mapping, colocalization, and summary statistics interpretation, is a plus.
• Familiarity with human disease genetics resources (e.g., GWAS Catalog, OMIM, ClinVar, Open Targets, GTEx), multi-omics data integration, and biomedical ontologies is also a plus.
• Familiarity with vector databases and retrieval-augmented generation (RAG) for scientific knowledge retrieval