Senior Data Scientist, AI Retrieval Systems

This is a fully remote position, open to applicants in United States.

📋 Description

• Model biomedical knowledge for research on rare diseases by integrating disease and phenotype ontologies as well as controlled vocabularies into PostgreSQL.

• Maintain release and refresh pathways, reconcile identifiers across various sources, and assess term hierarchies for clinical significance.

• Develop retrieval-augmented services that connect everyday language with clinical concepts.

• Optimize keyword and vector searches across extensive biomedical corpora while managing recall and latency trade-offs.

• Create ranking and relevance layers that incorporate domain-specific weighting and ensure graceful degradation.

• Deliver user interfaces using Next.js, React, and TypeScript, which include question and confirmation flows, result presentations, and live pipeline statuses.

• Continuously deploy to NIH on-premises and high-performance computing Kubernetes environments utilizing Helm charts, StatefulSets, secrets, ingress, GPU scheduling, and scheduled jobs.

• Construct and sustain evaluation systems as regression suites for retrieval and concept mapping.

• Capture request identifiers, latency, errors, and selected concepts for the review of AI-assisted results.

• Translate the needs of researchers, clinicians, and patient communities into data models, retrieval behavior, and interface design.

• Contribute to manuscripts, conference abstracts, and posters alongside NIH investigators, receiving authorship credit.

• Collaborate directly with NIH program staff, clinical geneticists, and specialists in rare disease information.

⛳️ Requirements

• Bachelor’s degree in Data Science, Computer Science, Bioinformatics, Biomedical Informatics, or a related discipline; equivalent professional experience may be accepted in lieu of a degree.

• Advanced degree is preferred.

• Minimum of 5 years of experience in building and operating production software or data systems.

• At least 2 years of experience in delivering LLM-powered applications relied upon by users.

• Experience in developing retrieval systems from start to finish, including indexing, query formulation, and retrieval-quality assessment against actual data.

• Familiarity with evaluating systems that do not have a singular correct answer using golden sets, offline regression suites, Recall@K, or MRR.

• Experience with structured output and tool/function invocation using typed schemas and validation.

• Capability to manage a service comprehensively, from schema design through deployment and operation.

• Ability to obtain and maintain a Public Trust Security clearance.

• Proficiency in Python with FastAPI, Pydantic, and pytest.

• Experience with PostgreSQL, including vector search, full-text search, embedding pipelines, indexing, and query optimization.

• Knowledge in LLM application engineering, including provider APIs and gateways, prompt/context design, structured generation, and tool utilization.

• Experience with data ingestion and transformation pipelines that have a repeatable refresh process.

• Familiarity with containers and Kubernetes.

• Proficiency in Next.js, React, and TypeScript.

• Experience with Git-based collaboration and CI/CD practices.

🏝️ Benefits

• 100% Medical, Dental & Vision Coverage for Employees.

• Paid Time Off and Paid Holidays.

• 401K match up to 5%.

• Educational Benefits for Career Growth.

• Employee Referral Bonus.

• Flexible Spending Accounts: Healthcare (FSA), Parking Reimbursement Account (PRK), Dependent Care Assistant Program (DCAP), Transportation Reimbursement Account (TRN).