Agentic AI Security Engineer
Howard Hughes Medical Institute
Summary
AI@HHMI at Janelia integrates AI agents across the research process. These tools write and execute code, optimize experimental and model parameters, and drive instruments. Letting AI agents act on shared research infrastructure requires serious safety engineering. The relevant failure mode is usually not a malicious attacker but a capable, misdirected tool running with legitimate user permissions at machine speed: hallucinated commands, instructions hijacked by retrieved content, runaway loops, sandbox escapes. We are hiring the engineer who owns this problem.
Job description
The role
You will research, develop, deploy, operate, and analyze the safety stack for agentic AI at Janelia:
- Sandboxing. Hardened, reproducible execution environments for agent code (kernel- and VM-level isolation, network egress control) on our OpenShift platform and HPC cluster, validated by adversarial testing.
- Guardrails. Policy enforcement on agent inputs, outputs, and tool calls; judge models; human approval gates; independent safeguard services that sessions can be routed through, individually or chained.
- Observability. Attributable audit logging, full-trace capture, real-time monitoring, and post-incident analysis of agent sessions.
You will join early enough to make the foundational architecture decisions, and you will operate what you design. We expect and support open-sourcing and publishing this work.
The environment
A large NVIDIA GPU cluster (B300/H200/H100 class) running self-hosted open-weight models and frontier commercial models; collaborations with industry (Anthropic and Google); scientists across biology, physics, and ML as your users; the long-term stability of a philanthropy-funded research institute.
What we look for
- Hands-on experience operating LLM agents and dealing with their failures, or deep sandbox/container-security expertise with clear ability to move into the agentic domain.
- Linux and Kubernetes/OpenShift isolation depth, including a precise understanding of the difference between containerization and sandboxing.
- Working knowledge of agent architectures: tool-calling protocols (e.g., MCP), approval gates, judge models, guardrail frameworks, and the limits of each.
- Evidence over certifications: open-source contributions, publications or technical writing, disclosed findings, or production systems you can discuss in depth.
- Minimum 5 years in security, systems/SRE, or ML systems engineering.
Requirements
- Hands-on experience operating LLM agents and dealing with their failures, or deep sandbox/container-security expertise with clear ability to move into the agentic domain.
- Linux and Kubernetes/OpenShift isolation depth, including a precise understanding of the difference between containerization and sandboxing.
- Working knowledge of agent architectures: tool-calling protocols (e.g., MCP), approval gates, judge models, guardrail frameworks, and the limits of each.
- Evidence over certifications: open-source contributions, publications or technical writing, disclosed findings, or production systems you can discuss in depth.
- Minimum 5 years in security, systems/SRE, or ML systems engineering.
Benefits
- Competitive pay
- Exceptional health benefits
- Retirement plans
- Time off
- Recognition programs
- Wellness programs
Company overview
The Howard Hughes Medical Institute (HHMI) is a premier American non-profit biomedical research organization and philanthropy founded in 1953 by business magnate Howard Hughes. Headquartered in Chevy Chase, Maryland with additional facilities at the Janelia Research Campus in Ashburn, Virginia, HHMI is one of the largest private funding organizations for biological and medical research in the United States. With an endowment of approximately $24 billion, it ranks as the second-wealthiest philanthropic organization in the country. HHMI supports over 300 investigators at more than 60 host institutions across the nation, investing about $825 million annually in biomedical research. The institute focuses on fundamental biological research across diverse fields including genetics, immunology, molecular biology, neuroscience, and structural biology. Beyond research funding, HHMI also supports innovative science education programs, curriculum development, and public engagement initiatives to inspire the next generation of scientists. The organization operates with approximately 2,300 employees and maintains a commitment to open science, requiring immediate open access to publications from its funded research since 2022.