Application Guide

How to Apply for GenAI Cyber Security Expert

at Alice

🏢 About Alice

Alice is a trust, safety, and security AI company that builds guardrails and red-teaming capabilities for frontier AI models, with a focus on high-stakes domains like industrial cybersecurity and CBRNE threats. Working there means being at the intersection of AI safety and national security, where your work directly hardens models against misuse in critical infrastructure attacks. The remote-first, US-based team likely collaborates with government, defense, and critical infrastructure partners, offering a mission-driven environment for security researchers who want to shape AI safety policy and practice.

About This Role

As a GenAI Cyber Security Expert at Alice, you will red-team generative AI systems to uncover vulnerabilities in industrial cybersecurity and CBRNE threat scenarios, specifically targeting SCADA, ICS, and critical infrastructure. You'll design adversarial prompts, jailbreaks, and multi-turn attacks to test whether models can be manipulated into assisting industrial attacks via payload generation, reconnaissance, or aggregating benign inputs. Your findings will directly inform safety teams, shape model safeguards, and contribute to building repeatable test suites and adversarial datasets that protect against real-world cyber-physical threats.

💡 A Day in the Life

A typical day might involve designing and executing adversarial prompt sequences against a GenAI model to test if it can be manipulated into generating SCADA exploit code or reconnaissance steps for an ICS network. You'd document failure modes, assign severity scores, and collaborate with safety engineers to improve guardrails, while also building automated test suites and adversarial datasets for repeatable evaluations. You'd likely spend time researching new ICS/OT attack techniques and GenAI jailbreak methods to keep your red-teaming approach cutting-edge.

🚀 Application Tools

Generate Cover Letter

AI-powered, tailored for Alice

Interview Prep

Practice questions for this role

🎯 Who Alice Is Looking For

  • Deep hands-on experience with industrial control systems (SCADA, PLCs, ICS/OT protocols like Modbus, DNP3, OPC UA) and a proven track record of red-teaming or penetration testing in cyber-physical environments.
  • Demonstrated aptitude for GenAI adversarial testing, including crafting jailbreaks, multi-turn attacks, and prompt injection techniques, with familiarity with LLM architectures and safety guardrails.
  • Strong technical writing skills to document failure modes, classify severity (e.g., CVSS or similar), and produce clear methodology and findings reports for safety and engineering teams.
  • Experience building repeatable test suites, adversarial datasets, and automation for red-teaming at scale, ideally in a research or product security context.
  • Knowledge of CBRNE threat scenarios and how AI could be misused for reconnaissance, payload generation, or aggregating benign inputs into harmful outputs.

📝 Tips for Applying to Alice

1

Highlight specific ICS/OT red-teaming projects: name the protocols (e.g., Modbus, Profinet), the types of PLCs or SCADA systems you've tested, and any cyber-physical attack chains you've demonstrated.

2

Showcase GenAI adversarial work by linking to public jailbreak examples, prompt injection write-ups, or GitHub repos of adversarial datasets you've created—even personal projects count.

3

Emphasize your ability to classify severity and document failure modes: provide examples of reports or test suites you've built, and mention any frameworks (e.g., MITRE ATT&CK for ICS, OWASP LLM Top 10) you've used.

4

Tailor your resume to include both industrial cybersecurity and AI red-teaming keywords, as Alice likely uses automated screening for both domains.

5

In your outreach or cover letter, reference Alice's mission in trust, safety, and security AI, and explain why you want to apply your ICS expertise to GenAI safety rather than traditional pentesting.

✉️ What to Emphasize in Your Cover Letter

Your cover letter should emphasize: (1) your deep ICS/OT red-teaming experience with concrete examples of protocols, PLCs, and attack chains you've tested; (2) your hands-on GenAI adversarial testing skills, including jailbreaks, multi-turn attacks, and dataset creation; (3) your ability to document and classify failure modes with severity ratings, ideally referencing frameworks like MITRE ATT&CK for ICS or OWASP LLM Top 10; and (4) your motivation to protect critical infrastructure by hardening AI models, aligning with Alice's mission in trust, safety, and security AI.

Generate Cover Letter →

🔍 Research Before Applying

To stand out, make sure you've researched:

  • → Explore Alice's website (alice.io) and any public blog posts, papers, or press releases to understand their specific approach to trust, safety, and security AI, especially in industrial or CBRNE domains.
  • → Research recent GenAI red-teaming incidents and published jailbreaks targeting critical infrastructure or industrial control systems to speak intelligently about current threats.
  • → Familiarize yourself with relevant frameworks like MITRE ATT&CK for ICS, OWASP LLM Top 10, and NIST guidelines for AI safety and critical infrastructure cybersecurity.
  • → Look up Alice's leadership and team backgrounds on LinkedIn to understand their expertise and tailor your application to their technical focus areas.
Visit Alice's Website →

💬 Prepare for These Interview Topics

Based on this role, you may be asked about:

1 How would you design a multi-turn adversarial prompt to test if an LLM can generate a payload for a PLC exploit, and what safeguards would you expect to bypass?
2 Walk us through a cyber-physical attack chain you've red-teamed in a SCADA or ICS environment—what were the key vulnerabilities and how did you document them?
3 What methods do you use to classify the severity of AI failure modes in industrial contexts, and how would you prioritize findings for safety teams?
4 Describe how you would build a repeatable test suite and adversarial dataset for evaluating GenAI models against CBRNE threat scenarios.
5 How do you stay current with both ICS/OT threats and GenAI adversarial techniques, and how would you apply that to Alice's red-teaming efforts?
Practice Interview Questions →

⚠️ Common Mistakes to Avoid

  • Focusing only on traditional IT cybersecurity without demonstrating specific ICS/OT or SCADA experience—this role requires deep industrial control systems knowledge.
  • Treating GenAI red-teaming as generic prompt engineering without showing structured adversarial testing, dataset creation, or severity classification.
  • Submitting a generic cover letter that doesn't connect your experience to Alice's mission in trust, safety, and security AI for critical infrastructure and CBRNE threats.

📅 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!

← Back to Job Listing Apply Now →