Application Guide

How to Apply for Red Team Engineer

at Gray Swan

🏢 About Gray Swan

Gray Swan is at the forefront of AI security, specializing in automated risk assessment for AI models. Joining this team means you'll be part of a mission-driven company that shapes the safety and reliability of frontier AI systems, working with top-tier researchers and engineers in a remote-first environment.

About This Role

As a Red Team Engineer, you will design and execute sophisticated attacks on cutting-edge AI systems, uncovering vulnerabilities that could have real-world impact. Your work will directly influence the security posture of AI deployments and contribute to the broader field of AI safety, making it a highly impactful role for those passionate about adversarial ML.

💡 A Day in the Life

A typical day might start with a stand-up meeting with your remote team to align on ongoing red teaming engagements. You'll spend time designing and executing adversarial attacks on AI models, documenting your findings in detailed reports, and collaborating with engineers to build internal tools for break verification. The role offers flexibility, but also requires disciplined time management to meet deadlines across multiple projects.

🎯 Who Gray Swan Is Looking For

  • Has 1+ years of hands-on experience in AI red teaming, adversarial ML, or security research, with a portfolio of discovered vulnerabilities or published research.
  • Possesses deep knowledge of prompt injection, tool use, agent exploitation, and multimodal attack surfaces, and can think creatively to bypass safeguards.
  • Strong technical writing skills to document findings clearly and deliver actionable security reports to both technical and non-technical stakeholders.
  • Self-motivated and able to work independently across multiple concurrent engagements, managing time effectively in a remote setting.

📝 Tips for Applying to Gray Swan

1

Tailor your resume to highlight specific AI red teaming projects or CTF challenges you've led, quantifying the impact (e.g., 'Discovered 15 critical vulnerabilities in a leading LLM').

2

Include links to your GitHub, blog posts, or write-ups of past red teaming exercises to demonstrate your practical skills and technical writing.

3

In your cover letter, mention your familiarity with Gray Swan's tools and publications, and how your experience aligns with their mission of automated AI risk assessment.

4

Be prepared to discuss a recent AI security breach or vulnerability you've analyzed, showing your awareness of current threats and mitigation strategies.

5

Since the role involves building internal tools, highlight any software development experience, especially in Python or other scripting languages, and your ability to create automation for security testing.

✉️ What to Emphasize in Your Cover Letter

["Emphasize your hands-on experience in AI red teaming, providing specific examples of attacks you've executed and the impact of your findings.", 'Highlight your technical writing skills, as the role requires delivering actionable security findings that are clear and concise.', 'Showcase your ability to work independently and manage multiple projects, as the role is remote and requires self-direction.', "Express enthusiasm for Gray Swan's mission to automate AI risk assessment and your desire to contribute to the safety of frontier AI systems."]

Generate Cover Letter →

🔍 Research Before Applying

To stand out, make sure you've researched:

  • → Read Gray Swan's website and any public blog posts or research papers to understand their tools and methodologies.
  • → Familiarize yourself with their Arena competitions and any public write-ups of past challenges to grasp the nature of the adversarial scenarios they design.
  • → Research the broader AI security landscape, including recent red teaming reports from other organizations (e.g., Anthropic, OpenAI) to understand industry best practices.
  • → Look into the backgrounds of the founders or key team members via LinkedIn to understand the company culture and technical focus.
Visit Gray Swan's Website →

💬 Prepare for These Interview Topics

Based on this role, you may be asked about:

1 Walk me through a red teaming engagement you led. How did you identify vulnerabilities and what was the outcome?
2 How would you design an adversarial scenario to test an AI system's resistance to prompt injection in a tool-use context?
3 Describe a time you had to write a technical report for a non-technical audience. How did you ensure clarity?
4 What are the most common vulnerabilities you've seen in multimodal AI systems, and how would you approach exploiting them?
5 How do you stay updated on the latest AI security research, and can you cite a recent paper or finding that influenced your approach?
Practice Interview Questions →

⚠️ Common Mistakes to Avoid

  • Don't submit a generic resume or cover letter that doesn't mention AI red teaming or specific relevant skills like prompt injection.
  • Avoid being vague about your experience; provide concrete examples and metrics to demonstrate your impact.
  • Don't overlook the technical writing requirement; ensure your application materials are well-written and demonstrate your ability to communicate complex ideas clearly.

📅 Application Timeline

This position is open until filled. However, we recommend applying as soon as possible as roles at mission-driven organizations tend to fill quickly.

Typical hiring timeline:

1

Application Review

1-2 weeks

2

Initial Screening

Phone call or written assessment

3

Interviews

1-2 rounds, usually virtual

✓

Offer

Congratulations!

Ready to Apply?

Good luck with your application to Gray Swan!