Senior Data Scientist, Agentic AI Systems

Stack

Responsibilities

• ▹Build agentic AI systems for rare disease research workflows: the conversation logic, the rules that decide when enough information has been gathered, and the confirmation steps that catch a misreading before it reaches anything downstream
• ▹Model outputs in Pydantic and use structured output and tool calling, so every field a model produces is typed, validated and traceable back to its source
• ▹Write, version and regression test the prompts behind clinical and scientific reasoning tasks; prompts and output schemas are treated as code, with tests to match
• ▹Build evaluation for tasks that have no single right answer: golden sets, offline regression suites and model-based graders good enough to decide what ships
• ▹Keep multi-step LLM workflows responsive under load: async design, concurrency limits, streaming partial results to the client, and timeout and failure handling
• ▹Log what the system does and why: request identifiers, latency, errors and the reasoning behind each automated choice, so staff can review an AI-assisted result
• ▹Work out what researchers, clinicians and patient communities need and turn it into data models and system behavior
• ▹Contribute to manuscripts, conference abstracts and posters with NIH investigators, credited as an author on work you helped produce
• ▹Own major components from design through deployment and help set the engineering standards for how AI gets applied on the team

Requirements

• ▹Bachelor's degree in Data Science, Computer Science, Bioinformatics, Biomedical Informatics or a related field (advanced degree preferred; equivalent professional experience considered)
• ▹At least 5 years building and operating production software or data systems, including at least 2 years shipping LLM-powered applications (agents, retrieval or evaluation) that people depend on; depth in agentic workflow engineering is weighed more heavily than total years
• ▹Experience with structured output and tool or function calling: constraining a model to a typed schema and validating what came back
• ▹Experience evaluating systems that have no single right answer, using golden sets, offline regression suites or model-based graders
• ▹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, with FastAPI, Pydantic and pytest
• ▹LLM application engineering: provider APIs and gateways, prompt and context design, structured generation, tool use and tracing
• ▹PostgreSQL, including work with embeddings or vector search alongside relational data
• ▹Asynchronous and concurrent Python, plus streaming results to a client
• ▹Containers and Kubernetes, enough to ship, debug and operate a service on infrastructure you do not administer
• ▹Git-based collaboration and CI/CD in a shared codebase

Nice to have

• ▹A typed agent framework such as Pydantic AI, LangGraph or the OpenAI or Anthropic agent SDKs, and MCP for tool integration
• ▹LLM tracing and evaluation tooling such as Langfuse, LangSmith, Arize Phoenix or Braintrust
• ▹Serving open-weight models in production with Ollama or vLLM behind a gateway such as LiteLLM
• ▹Biomedical ontologies and controlled vocabularies (MONDO, HPO, UMLS, MeSH and other OBO Foundry resources), with comfort working through term hierarchies, synonyms and cross references
• ▹Background in rare disease, clinical genetics or translational research
• ▹Experience working alongside clinicians, curators or patient advocacy organizations, and translating their vocabulary into a data model that holds up
• ▹Published or presented work that explains your engineering to people who did not build it (peer-reviewed papers, conference talks, preprints, technical blog posts, open source contributions)
• ▹Prior or current NIH experience

Soft skills

What we offer

• ▹100% medical, dental and 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 (PRK), dependent care (DCAP) and transportation reimbursement (TRN)
• ▹Base salary of $130,000 to $150,000 depending on experience, qualifications, skills and location

About the company

Axle is a bioscience and information technology company offering translational research, biomedical informatics and data science solutions to research centers and healthcare organizations, including multiple institutes at the National Institutes of Health (NIH).