Principal AI Vulnerability Researcher — Lead Defenses

AIBound; United States; On-site; USD 180,000 - 230,000; Full time

Job summary

AIBound is hiring a Principal AI Vulnerability Researcher to break the harness layer before an adversary does, and to turn what you break into shipped defences. This is a founding research hire with hands-on work and an opportunity to grow the function into a team as the work scales.

You will own the research agenda, publish write-ups and CVEs, mentor researchers, and report directly to the CEO, shaping AIBound's public voice in AI security.

Qualifications

• 6+ years in offensive security, vulnerability research, exploit development or detection engineering; includes AI/LLM or agentic systems.
• Demonstrated original research: CVEs, advisories, conference talks, bug bounty results or offensive tooling.
• Deep macOS and Linux internals and shell command parsing; ability to recognize deceptive command appearances.
• Strong Python and shell scripting; comfortable writing enforcement code.
• Working knowledge of agent architectures — tool calling, MCP, skills, memory; assess trust boundaries.
• Sound judgement on responsible research; safe sandbox work and coordinated disclosure by default.

Responsibilities

• Attack the Harness enforcement path as adversary would; policy delivery, tampering, endpoint policy files, decision hooks, and gaps between allow/deny and execution.
• Discover and weaponize novel attacks on coding agents and the AI supply chain: prompt injection, tool-call hijacking, context poisoning, malicious MCP servers, skills and sub-agents.
• Turn findings into shipped detection — deterministic rules, decision hooks and LLM-assisted classifiers — proven on a labelled benchmark corpus before customer deployment.
• Track frontier; translate into roadmap input; publish write-ups, talks and CVEs to establish AIBound as a research voice.
• Grow the function — set research agenda, hire and mentor researchers as the team scales.

Skills

Offensive security

Vulnerability research

Exploit development

Detection engineering

Python

Shell scripting

LLM/agentic systems

Research leadership

Adversary simulations

Job description

AIBound is hiring a Principal AI Vulnerability Researcher to break the harness layer before an adversary does, and to turn what you break into shipped defences. This is a founding research hire with hands-on work and an opportunity to grow the function into a team as the work scales.

You will own the research agenda, publish write-ups and CVEs, mentor researchers, and report directly to the CEO, shaping AIBound's public voice in AI security.