CareerPlanSign in

AI Security Researcher II

United States, Washington, Redmond💼 Full-time🗓 2026-07-29 → 2026-09-26

Core

Formulate and investigate research questions at the intersection of cybersecurity and agentic AI behavior, including security risks, failure modes, and adversarial behavior in agentic AI systems.

Role type

Research-level AI security researcher (agentic systems)

Builds

Research insights, methodologies, and mitigations that advance the security of AI systems

Domain

Cybersecurity + Agentic AI

Deliverable

research

Required skills

Designing experiments, evaluations, and benchmarks for autonomous, tool-using, and multi-agent systems; Analyzing results to develop research insights and mitigations; Connecting research findings to practical security guidance for real-world AI products

Preferred skills

Experience with adversarial machine learning; Experience with LLM evaluation; Experience with open-source tools or research artifacts

Technologies

agentic AI systems, autonomous systems, tool-using systems, multi-agent systems, LLMs

Responsibilities

Design rigorous experiments, evaluations, and benchmarks for autonomous, tool-using, and multi-agent systems; Analyze results and develop research insights, methodologies, and mitigations that advance the security of AI systems; Formulate and investigate research questions at the intersection of cybersecurity and agentic AI behavior

Sourced via microsoft · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.