Team Summary
Our platform manages over 125 petabytes of data, processes 50 billion records, and handles 3 billion API calls monthly. With thousands of users depending on us, there is a clear imperative to leverage powerful frontier LLM models and execute on DNAnexus’ Agentic Platform. The platform enables agent-based systems to provide clinical and molecular data workflows in a highly scalable and regulated (PHI) environment. The goal is to enable more intelligent, automated, and reliable execution of complex scientific data processes in the cloud.
We’re Looking For
- A strong background in bioinformatics, computational biology, or a related scientific field. Candidates who can help us nurture this knowledge within the team.
- Extensive experience with large-scale data processing and analysis pipelines (e.g., WES, WGS, RNA-Seq).
- Experience developing and integrating with LLMs, RAG systems, or other agentic frameworks for scientific data workflows is highly desirable.
- Proficiency with relevant bioinformatics tools and databases, we will integrate this to Agentic pipelines
Responsibilities
- Design, develop, and deploy core components of the DNAnexus Agentic Platform, focusing on robust, scalable, and secure systems for genomic and multi-omic data analysis.
- Integrate advanced LLM capabilities and RAG (Retrieval-Augmented Generation) systems to create intelligent, automated, and auditable scientific workflows.
- Collaborate with bioinformatics scientists and product managers to translate complex biological research needs into high-quality software solutions.
- Share bioinformatics knowledge within the team of engineers
- Stay current with the latest advancements in AI, LLMs, and bioinformatics technology to drive platform innovation.