Application Guide

How to Apply for AI Cyber Red Teamer

at Trajectory Labs, PBC

🏢 About Trajectory Labs, PBC

Trajectory Labs, PBC is a startup building reinforcement learning environments specifically for frontier AI labs to train robust, secure, and reliable models. Unlike typical AI safety companies, they focus on adversarial training—actively attacking models to harden them before deployment. Working here means directly shaping the security posture of next-generation AI systems alongside top labs.

About This Role

As an AI Cyber Red Teamer, you will design and execute novel attacks against frontier AI model safeguards, aiming to jailbreak or bypass guardrails to uncover cyber vulnerabilities. You'll document these failures and feed them into training improvements, directly influencing how models are hardened. This role is on the front lines of AI security, with your findings potentially preventing real-world exploits.

💡 A Day in the Life

You might start by reviewing a new model release, brainstorming attack vectors, then scripting automated probes to test guardrails. Afternoon could involve documenting a successful jailbreak, sharing findings with the training team, and iterating on attack strategies based on feedback. Expect a highly collaborative, fast-paced environment where your creativity directly impacts model security.

🚀 Application Tools

Generate Cover Letter

AI-powered, tailored for Trajectory Labs, PBC

Interview Prep

Practice questions for this role

🎯 Who Trajectory Labs, PBC Is Looking For

  • Proven track record of successful jailbreaks against frontier models (e.g., GPT-4, Claude, Gemini) with documented examples.
  • Offensive security mindset with self-directed problem-solving, demonstrated through pentesting, red teaming, exploit development, or CTF competitions.
  • Strong Python scripting and command-line proficiency, plus experience with agentic coding tools (e.g., Cursor, Copilot, or custom agents).
  • Deep curiosity about AI guardrail mechanisms and ability to think creatively about bypassing them.

📝 Tips for Applying to Trajectory Labs, PBC

1

Include concrete examples of successful jailbreaks you've performed, with links to write-ups or GitHub repos—this is the single most important proof of skill.

2

Highlight any CTF or red teaming competition results (e.g., DEF CON CTF, Hack The Box) and explain how your approach translates to AI guardrails.

3

Demonstrate familiarity with Trajectory Labs' mission by referencing their RL environment work and how your attacks would improve model robustness.

4

Show proficiency with agentic coding tools by describing a project where you used them to automate attack generation or vulnerability discovery.

5

If you have open-source contributions related to AI security or adversarial ML, prominently feature them in your application.

✉️ What to Emphasize in Your Cover Letter

Emphasize specific jailbreak successes and the methodology behind them; explain why attacking AI guardrails is crucial for safe deployment; showcase your offensive security background (pentesting, CTFs) and how it applies to AI; and express enthusiasm for Trajectory Labs' RL-based approach to training robust models.

Generate Cover Letter →

🔍 Research Before Applying

To stand out, make sure you've researched:

  • → Read Trajectory Labs' website and any published papers or blog posts about their RL environments for AI training.
  • → Study recent jailbreak techniques and adversarial ML research (e.g., from papers like 'Universal and Transferable Adversarial Attacks on Aligned Language Models').
  • → Investigate the frontier AI labs they partner with (e.g., OpenAI, Anthropic, DeepMind) and their safety/security challenges.
  • → Explore public CTF write-ups and red teaming reports to understand the state of the art in offensive security.
Visit Trajectory Labs, PBC's Website →

💬 Prepare for These Interview Topics

Based on this role, you may be asked about:

1 Walk us through a specific jailbreak you designed: what was the model, what was the guardrail, and how did you bypass it?
2 How would you approach discovering novel attack vectors against a new frontier model with unknown safeguards?
3 Describe a time you used Python or agentic coding tools to automate part of a red teaming task.
4 What are the limitations of current AI guardrails, and how would you exploit them?
5 How do you document and communicate vulnerabilities to both technical and non-technical stakeholders?
Practice Interview Questions →

⚠️ Common Mistakes to Avoid

  • Claiming jailbreak experience without concrete, verifiable examples—this role demands proof, not just claims.
  • Focusing only on traditional cybersecurity without connecting it to AI guardrails—show you understand the unique challenges of AI red teaming.
  • Submitting a generic cover letter that doesn't mention Trajectory Labs' specific mission or the RL environment aspect.

📅 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 Trajectory Labs, PBC!

← Back to Job Listing Apply Now →