Red Team Engineer Safeguards
Anthropic
Job Overview
Who's the hiring manager?
Sign up to PitchMeAI to discover the hiring manager's details for this job. We will also write them an intro email for you.
Job Description
About Anthropic
Anthropic’s mission is to create reliable, interpretable, and steerable AI systems that are safe and beneficial for users and society. The company is a quickly growing team of researchers, engineers, policy experts, and business leaders.
About the Role
As a Red Team Engineer Safeguards at Anthropic, you will take an adversarial approach to uncover vulnerabilities in deployed AI systems and products before they can be exploited. You will work across technical infrastructure and handle emergent risks from advanced AI capabilities.
Responsibilities
- Conduct comprehensive adversarial testing across Anthropic’s product surfaces.
- Research and implement novel testing approaches for emerging capabilities.
- Design and execute 'full kill chain' attacks emulating real-world threat actors.
- Develop and maintain systematic testing methodologies and automated frameworks.
- Collaborate with Product, Engineering, and Policy teams to translate findings into concrete improvements.
- Help establish metrics for measuring detection effectiveness of novel abuse.
Qualifications
You may be a good fit if you have:
- Experience in penetration testing, red teaming, or application security.
- Strong technical skills in web application security with hands-on expertise using tools like Burp Suite, Metasploit.
- Demonstrated ability to discover novel attack vectors and chain vulnerabilities creatively.
- Public work such as CVEs, blog posts, or bug bounty reports.
- Ability to build custom automation and adaptability to emerging threats.
- Excellent communication skills to explain technical concepts to varied audiences.
Strong candidates may also have experience with AI/ML security, API security, anti-fraud systems, distributed systems, and a background in abuse prevention.
Compensation & Logistics
- Annual Salary: 300,000 - 320,000 USD
- Education: Bachelor’s degree or equivalent experience required.
- Work Arrangement: Hybrid (at least 25% in-office presence).
- Visa Sponsorship: Available for select candidates.
How We're Different
At Anthropic, work is collaborative and focused on large-scale research efforts that advance trustworthy and steerable AI systems. Communication and impact are valued in a cohesive team environment.
Key skills/competency
- Penetration Testing
- Red Teaming
- Application Security
- Adversarial Testing
- Automation
- Vulnerability Assessment
- Web Security
- Custom Scripting
- Collaboration
- AI Safety
How to Get Hired at Anthropic
- Customize your resume: Align skills with red teaming and security testing.
- Highlight relevant experience: Showcase penetration testing and automation work.
- Research Anthropic: Understand its mission and AI safety focus.
- Prepare technical examples: Illustrate past full kill chain simulations clearly.
Frequently Asked Questions
Find answers to common questions about this job opportunity
Explore similar opportunities that match your background