Application Guide

How to Apply for GenAI Chemical, Biological, Radiological, Nuclear, and Explosives Cyber Security Expert

at Alice

🏢 About Alice

Alice is a trust, safety, and security AI company that builds technology to make AI systems safer and more reliable. Working here means contributing to cutting-edge AI security research with real-world impact, especially in high-stakes domains like CBRNE and industrial environments. The remote-first culture and focus on adversarial testing make it ideal for those who want to stay ahead of emerging AI threats.

About This Role

As a GenAI CBRNE Cyber Security Expert, you'll be on the front lines of AI security, adversarially testing GenAI models to uncover vulnerabilities that could be exploited in chemical, biological, radiological, nuclear, and explosives contexts. You'll design sophisticated prompts and jailbreaks to probe model boundaries, evaluate attack feasibility, and document findings to inform safety and alignment improvements. This role is critical for ensuring that powerful AI systems cannot be manipulated to cause harm in the physical world.

💡 A Day in the Life

A typical day might involve brainstorming novel adversarial prompts, running experiments against GenAI models, and analyzing results for potential vulnerabilities. You'll collaborate with safety and alignment teams to prioritize findings, document failure modes, and update test suites. You'll also spend time researching emerging AI attack techniques and CBRNE threats to stay ahead of adversaries.

🎯 Who Alice Is Looking For

  • Deep expertise in adversarial testing of AI systems, including prompt engineering, jailbreaking, and multi-turn evaluation techniques.
  • Background in cybersecurity, particularly in industrial control systems (ICS), SCADA, or CBRNE threat landscapes, with an understanding of how AI could enable attacks.
  • Experience with red teaming or security research, including building test suites and datasets, and classifying vulnerabilities by severity.
  • Strong analytical and documentation skills, with the ability to communicate complex technical findings to cross-functional teams like safety and alignment.

📝 Tips for Applying to Alice

1

Highlight any experience you have with adversarial AI testing or red teaming, especially if it involves safety-critical domains. Use concrete examples of vulnerabilities you've discovered or test suites you've built.

2

Tailor your resume to emphasize CBRNE or industrial security knowledge. If you have worked on ICS/SCADA security or threat intelligence for critical infrastructure, make that prominent.

3

Showcase your ability to design multi-turn evaluations and jailbreaks. Provide a portfolio or GitHub link with examples of adversarial prompts you've created (ensure no sensitive info is exposed).

4

Demonstrate familiarity with AI safety and alignment concepts. Mention any collaboration with safety teams or contributions to responsible AI initiatives.

5

Since Alice is remote-first, emphasize your ability to work independently and asynchronously. Highlight past remote work successes and self-driven research projects.

✉️ What to Emphasize in Your Cover Letter

In your cover letter, focus on: (1) a specific instance where you identified a novel AI vulnerability and its potential impact in a CBRNE or industrial context; (2) your methodology for designing adversarial tests and how you ensure comprehensive coverage; (3) your understanding of the intersection between AI security and physical-world threats, and why it matters; (4) your enthusiasm for Alice's mission and how your skills align with their trust, safety, and security goals.

Generate Cover Letter →

🔍 Research Before Applying

To stand out, make sure you've researched:

  • → Explore Alice's website and blog to understand their specific approach to AI trust, safety, and security, and any published research on adversarial testing.
  • → Research recent AI safety incidents or vulnerabilities related to CBRNE, such as prompt injection attacks that could generate dangerous instructions.
  • → Familiarize yourself with industrial control system security frameworks (e.g., NIST, IEC 62443) and how AI might be used in attacks.
  • → Look into Alice's leadership and team backgrounds to understand their expertise and potential interview focus areas.
Visit Alice's Website →

💬 Prepare for These Interview Topics

Based on this role, you may be asked about:

1 How would you approach designing an adversarial test suite to evaluate a GenAI model's potential to assist in a chemical weapon attack?
2 Describe a time you discovered a critical vulnerability in an AI system. How did you classify its severity and report it?
3 What are the key differences between adversarial testing for traditional software versus GenAI models?
4 How do you stay updated on emerging AI attack techniques and CBRNE threats?
5 Can you walk us through a multi-turn evaluation you've designed? What was the goal and what did you learn?
Practice Interview Questions →

⚠️ Common Mistakes to Avoid

  • Avoid generic applications that don't demonstrate specific knowledge of CBRNE or industrial security. This role requires niche expertise, so failing to address that will hurt your chances.
  • Don't oversell your AI experience if it's not directly related to adversarial testing or safety. Be honest about your background and show willingness to learn.
  • Avoid discussing ethical hacking without emphasizing responsible disclosure and safety-first mindset. Alice is a safety company, so they need to trust you'll use your skills ethically.

📅 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 Alice!