# Red Team Engineer, Safeguards

Hiring organization: [Menlo Ventures Portfolio](https://career.thegoodapps.co/organizations/menlo-ventures-portfolio)

Canonical page: https://career.thegoodapps.co/jobs/31ba2ee0-8961-4550-a413-3d1de6560c1c

Listed on Menlo Ventures Portfolio's own careers site. Applications go to them directly.

- Employment type: full time
- Location: San Francisco, CA
- Remote: yes
- Salary: 320000 – 405000 USD per year

## Summary

This role involves adversarial testing of AI systems and products to identify vulnerabilities before they can be exploited. It suits security professionals who want to shift their expertise toward novel threats in AI, combining traditional penetration testing with emerging safety challenges unique to large language models and agentic systems.

_Our summary, not Menlo Ventures Portfolio's wording._

## Skills named

Application Security, Burp Suite, Metasploit, Penetration Testing

## Required

- Penetration testing, red teaming, or application security experience
- Model jailbreaking and large-scale agentic workflow testing experience
- Web application security expertise with hands-on security testing tools
- Custom automation and LLM-specific testing framework development
- Track record of discovering novel attack vectors and chaining vulnerabilities
- Public security work (CVEs, blog posts, or bug bounty disclosures)
- Strong written and verbal communication skills

## Nice to have

- AI/ML security or adversarial machine learning experience
- AI safety knowledge beyond traditional security, including jailbreak guardrails
- API security and rate-limiting testing experience
- Business logic and authorization bypass testing background
- Anti-fraud, trust & safety, or abuse prevention systems experience
- Distributed systems and infrastructure security familiarity
- Abuse detection mechanism and bypass engineering experience
- Adaptability to emerging threat domains outside direct expertise

Apply on Menlo Ventures Portfolio's site: https://job-boards.greenhouse.io/anthropic/jobs/5320469008