Senior AI Security Researcher — Remote

VulnU; United States; Remote; USD 160,000 - 210,000; Full time

Job summary

Snyk in the United States (Remote) is seeking a Senior Security Researcher to advance offensive security for AI-enabled software. The role focuses on researching and exploiting weaknesses in LLM applications and autonomous agents, building attack tooling, and evaluating defenses to improve Snyk’s security products.

You will work on AI red teaming, exploit validation, and collaboration with engineers to translate findings into actionable remediation.

Qualifications

• Experience in AI red teaming and prompt injection.
• Web/API penetration testing, authentication/authorization flaws.
• Model behavior, inference, context management, and tool calling familiarity.
• Strong Python and APIs skills for research tooling.

Skills

AI red teaming

Offensive security

LLM fundamentals

Harness engineering

Agent security

Evals and benchmarks

Experiment design

Research engineering

Python

APIs

Containers

Browser automation

Tools

Python

APIs

Containers

Browser automation

Job description

Snyk in the United States (Remote) is seeking a Senior Security Researcher to advance offensive security for AI-enabled software. The role focuses on researching and exploiting weaknesses in LLM applications and autonomous agents, building attack tooling, and evaluating defenses to improve Snyk’s security products.

You will work on AI red teaming, exploit validation, and collaboration with engineers to translate findings into actionable remediation.