Agentic AI Scientist - Office of Data Science
About The Position
The Office of Data Science at St. Jude Children’s Research Hospital is seeking a skilled, collaborative Agentic AI Scientist to lead the design, development, and evaluation of agentic AI systems supporting research and operational workflows. The role focuses on building and orchestrating advanced LLM-based agents, developing secure and interoperable infrastructure, and translating emerging AI capabilities into practical, high-impact solutions. The scientist will contribute to technical reporting, results evaluation, and staff guidance to encourage responsible and effective adoption of agentic AI. This position reports to the Chief of Artificial Intelligence. The Office of Data Science works to expand St. Jude’s data science capabilities and enable collaboration among experimental, clinical, and data scientists to advance biological discovery and pediatric disease research.
Requirements
- Bachelor’s degree in Computer Science, Bioinformatics, Biomedical Engineering, or a related field and at least 6 years of relevant experience; alternatively, a master’s degree and at least 4 years of relevant experience; or an entry-level PhD with no work experience. The PhD requirement may be waived for an extraordinarily unusual level of scientific contribution.
- One to two first-author papers with a journal impact factor greater than 5, or equivalent contributions to other research or open-source outputs.
- Depth in at least one agent framework, with working awareness across the listed framework options.
- Ability to author and operate MCP servers, clients, and tools, including core primitives over JSON-RPC with OAuth 2.1 authorization; build A2A-interoperable agents; and maintain awareness of emerging agent standards.
- Knowledge of agent orchestration and control loops, including model-output parsing, tool dispatch, context-window management, stop conditions, budgets, safety boundaries, multi-agent topologies, checkpointing, human-in-the-loop controls, and composable agent capabilities.
- Experience with tracing, offline and online evaluation, guardrails, red-teaming, and observability tooling.
- Knowledge of agent identity and authorization, RBAC/SSO, sandboxed execution, and private or secure LLM deployment patterns.
- Strong Python skills and familiarity with version control, testing, CI, reproducible evaluation harnesses, retrieval and context engineering, and related techniques.
Nice To Haves
- Prior applied-ML or agentic-AI research experience.
- Demonstrated experience shipping LLM-integrated systems.
- Healthcare, biomedical, or other research-intensive domain experience.
- Experience in project coordination, maintenance, and other research support activities.
Responsibilities
- Lead computationally focused agentic-AI research and engineering projects with moderate supervision; advise on analytical approaches, set up experiments, and develop agentic methods with manager input.
- Design and orchestrate agent systems, including agent hierarchies, tool use, handoffs, checkpointing, and human-in-the-loop control, using ODS data and tools.
- Stand up and maintain MCP servers and clients and A2A-interoperable agents that connect ODS assets under secure, auditable, HIPAA-aligned patterns.
- Identify, process, organize, summarize, review, and report results; instrument agents with tracing, evaluations, and cost and latency budgets.
- Draft manuscripts and technical reports and take them through submission and internal review with manager input.
- Instruct and guide staff in agentic-AI techniques.
- Mentor others in agentic-AI best practices and standards.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Entry Level
