Agentic AI Scientist - Office of Data Science

St. Jude Children’s Research Hospital is where those with a passion for making a difference come to break new ground. Located in Memphis, Tennessee, St.Jude leads the world in understanding, treating, and defeating childhood cancer and other life‑threatening diseases through groundbreaking research and compassionate care.

The Office of Data Science (ODS) e institutionalizes and expands data science capabilities to unlock the vast potential of St.Jude’s biological data repositories. ODS seeks an Agentic AI Scientist to lead the design, development, and evaluation of agentic AI systems that support research and operational workflows across the Office of Data Science.

• Lead computationally focused agentic‑AI research and engineering projects with moderate supervision from the manager; provide inputs on analytical approaches, set up experiments, and develop new agentic methods with manager input.
• Design and orchestrate agent systems (agent hierarchies, tool use, handoffs, checkpointing, and human‑in‑the‑loop control) over ODS data and tools.
• Stand up and maintain MCP servers/clients and A2A‑interoperable agents that connect ODS assets (e.g., St.Jude Cloud, internal warehouses, planning systems) under secure, auditable, HIPAA‑aligned patterns.
• Identify, process, organize, summarize, review, and report results; instrument every agent with tracing, evaluations, and cost/latency budgets.
• Draft manuscripts and technical reports and work through submission and internal review with manager input; instruct and guide other staff in agentic‑AI techniques.
• Mentor others in agentic AI best practices and standards.

Minimum qualifications:

• Bachelor’s in Computer Science, Bioinformatics, Biomedical Engineering, or a related field with 6+ years of relevant experience (or Master’s with 4+ years).
• Entry‑level PhD with no work experience (PhD requirement waived, given an extraordinarily unusual level of scientific contribution).
• Publication benchmark: 1–2 first‑author papers in journals with impact factor > 5 (or equivalent contribution to other research / open‑source outputs).

Preferred qualifications:

• Prior applied‑ML or agentic‑AI research; demonstrated shipping of LLM‑integrated systems; experience in healthcare, biomedical, or other research‑intensive domain.
• Experience in project coordination, maintenance, and other research support activities.

Preferred Technical / Functional Requirements (Agentic AI specialization):

• Agent frameworks – production depth in at least one framework (e.g., Lang Graph, OpenAI Agents SDK, Google ADK, CrewAI, Microsoft Agent Framework, Pydantic AI, Llama Index, Strands, Haystack, DSPy, Agno).
• Interoperability protocols – author and operate MCP (Model Context Protocol) servers, clients, and tools, including core primitives over JSON‑RPC with OAuth 2.1 authorization; build A2A (Agent2
  
  Agent) interoperable agents; awareness of emerging agent standards.
• Orchestration & control loop – agent harness: model‑output parsing, tool dispatch, context‑window management, enforcement of stop conditions, budgets, safety boundaries; multi‑agent topologies (hierarchy, swarm, graph); checkpointing and human‑in‑the‑loop; composable, loadable agent capabilities.
• Evaluation & observability – tracing (e.g., Open Telemetry), offline and online evaluation (e.g., LLM‑as‑judge), guardrails, red‑team testing; observability tooling (e.g., Lang Smith, Langfuse, Arize Phoenix, Microsoft Foundry Observability).
• Identity, security & deployment – agent identity and authorization (e.g., Microsoft Entra Agent , Okta / Auth0 for AI Agents, On‑Behalf‑Of token exchange), RBAC/SSO, sandboxed execution (e.g., E2B, Modal, Firecracker microVM), private/secure LLM deployment patterns (HIPAA‑aligned, auditable, on‑prem/VPC).
• Engineering hygiene – strong Python; version control, tests, CI, reproducible eval harnesses; retrieval and context engineering (embeddings, vector search with pgvector or Pinecone, RAG, GraphRAG, cache‑augmented generation / CAG, agentic RAG, recursive language models / RLM).

Compensation:
The estimated salary range for this role is $86,320 – $154,960 per year.

St. Jude is an Equal Opportunity Employer.