Leads the team this role joins
Decides on early hires
Runs hiring at the company
From your own Gmail and LinkedIn.
About the role
This is a senior data scientist job at Axle, building the retrieval and knowledge layer for AI systems that support rare disease research at the National Institutes of Health. The job description places the role remote within the United States, while the listing board tags it as worldwide remote, so eligibility should be confirmed on the employer posting. It suits engineers with at least five years of production software experience who have shipped LLM applications and built retrieval systems. You would own the data layer, retrieval services, user-facing interfaces, and the deployment path onto NIH infrastructure.
What you’ll do
- Load disease and phenotype vocabularies into PostgreSQL with a repeatable release and refresh process, and reconcile identifiers across sources.
- Build retrieval-augmented services that map everyday language to clinical concepts, with a model choosing among candidates before any value is saved.
- Tune keyword and vector search over large biomedical corpora and justify the recall and latency trade-offs.
- Build ranking and relevance logic, including fallback behavior when a condition falls outside curated coverage.
- Build Next.js, React, and TypeScript interfaces for question flows, results, and pipeline status.
- Deploy and operate services on NIH on-premises and HPC Kubernetes, including Helm charts, StatefulSets, GPU scheduling, and scheduled jobs, working with operations teams.
- Build and maintain an evaluation suite that runs continuously as a regression test.
- Log requests, latency, errors, and selected concepts so staff can review AI-assisted results.
- Contribute to manuscripts, abstracts, and posters with NIH investigators, with authorship where it is earned.
What they’re looking for
- Bachelor's degree in data science, computer science, bioinformatics, biomedical informatics, or a related field, or equivalent professional experience.
- At least 5 years building and operating production software or data systems, including at least 2 years shipping LLM-powered applications such as agents, retrieval, or evaluation.
- End-to-end retrieval system experience, including indexing, query construction, and measuring retrieval quality.
- Experience evaluating systems that have no single right answer, using golden sets, regression suites, Recall@K, or MRR.
- Experience with structured output and tool or function calling, constraining models to typed schemas and validating results.
- Ability to own a service from schema design through deployment and operation.
- Ability to obtain and maintain a Public Trust security clearance.
- Python with FastAPI, Pydantic, and pytest.
- PostgreSQL in depth, including vector search, full-text search, embedding pipelines, indexing, and query tuning.
- LLM application engineering, including provider APIs, prompt and context design, structured generation, and tool use.
- Data ingestion and transformation pipelines with a repeatable refresh path.
- Containers and Kubernetes, enough to ship, debug, and operate services.
Nice to have
- Biomedical ontologies and controlled vocabularies such as MONDO, HPO, UMLS, MeSH, and OBO Foundry resources.
- Grounding model output in domain terminology through embedding retrieval and model disambiguation, such as entity linking or ontology alignment.
- Helm and deployment to on-premises or HPC Kubernetes environments.
- Serving open-weight models with Ollama or vLLM behind a gateway such as LiteLLM, and working with domain embedding models such as MedCPT.
- Background in rare disease, clinical genetics, or translational research.
- Contributions to open biomedical resources or standards, such as OBO Foundry ontologies or GA4GH.
- Published or presented work that explains engineering to general audiences.
- Prior or current NIH experience.
What’s on offer
- Salary range of $130,000-$150,000 USD, varying with experience, qualifications, skills, and location.
- 100 percent medical, dental, and vision coverage for employees.
- Paid time off and paid holidays.
- 401(k) match up to 5 percent.
- Educational benefits, an employee referral bonus, and flexible spending and reimbursement accounts, including healthcare FSA, parking, dependent care, and transportation.
Skills
Questions about this role
Is this Axle senior data scientist job remote?
The job description says the role is remote within the United States. The listing board tags it as worldwide remote, so check the employer posting for eligibility.
What is the salary range?
The range is $130,000-$150,000 USD, and actual pay depends on experience, qualifications, skills, and location.
Is a security clearance required?
Candidates must be able to obtain and maintain a Public Trust security clearance.
Is ontology experience required?
No. Candidates who meet the required qualifications but none of the preferred ones are encouraged to apply.