Senior Data Scientist, AI Retrieval Systems
A
AxleBiomedical informatics
Remote position within the United States.Full-TimeSenior
Salary130,000 - 150,000 USD per year
Apply NowOpens the employer's application page
Job Details
- Experience
- At least 5 years building and operating production software or data systems. At least 2 of those years should involve shipping LLM-powered applications (agents, retrieval, or evaluation) that people depend on.
- Required Skills
- PostgreSQLPythonKubernetesFastAPINext.jsReact
Requirements
- Bachelor's degree in Data Science, Computer Science, Bioinformatics, Biomedical Informatics, or a related field, or equivalent professional experience; an advanced degree is preferred.
- At least 5 years building and operating production software or data systems, including at least 2 years shipping LLM-powered applications.
- Experience building retrieval systems end to end, including indexing, query construction, and measuring retrieval quality against real data.
- Experience evaluating systems with no single right answer using golden sets, offline regression suites, or metrics such as Recall@K and MRR.
- Experience constraining model output to a typed schema and validating the results, including structured output and tool or function calling.
- Ability to own a service end to end, from schema design through deployment and operation.
- Ability to obtain and maintain a Public Trust Security clearance.
- Python experience with FastAPI, Pydantic, and pytest.
- Strong PostgreSQL experience, including vector search, full-text search, embedding pipelines, indexing, and query tuning.
- LLM application engineering experience with provider APIs and gateways, prompt and context design, structured generation, and tool use.
- Experience with data ingestion and transformation pipelines, containers, Kubernetes, Git-based collaboration, and CI/CD.
- Working comfort with Next.js, React, and TypeScript.
Responsibilities
- Ingest disease and phenotype ontologies and controlled vocabularies into PostgreSQL, reconcile identifiers, and maintain a release and refresh path.
- Build retrieval-augmented services that map everyday language to clinical concepts using embeddings, candidate retrieval, and model disambiguation.
- Tune keyword and vector search over biomedical corpora and manage recall and latency trade-offs.
- Build ranking and relevance layers, including domain-aware weighting and graceful degradation outside curated coverage.
- Deliver question and confirmation flows, result presentation, and live pipeline status interfaces in Next.js, React, and TypeScript.
- Deploy services to NIH on-premises and high-performance computing Kubernetes environments using tools and configurations including Helm charts, StatefulSets, secrets, ingress, GPU scheduling, and scheduled jobs.
- Build and maintain regression evaluation for retrieval and concept mapping.
- Log system activity, including request identifiers, latency, errors, and selected concepts, for staff review.
- Work with researchers, clinicians, and patient communities to translate needs into data models, retrieval behavior, and interface design.
- Contribute to manuscripts, conference abstracts, and posters with NIH investigators.
View Full Description & ApplyYou'll be redirected to the employer's site
