Security Engineer, Cybersecurity AI Evaluation

You will help improve large language models by creating cybersecurity prompts and judging how well the models respond. Your reviews should reflect practical security engineering or offensive security knowledge.

The work is remote and asynchronous. Project assignments may vary across cybersecurity evaluation activities.

• Create prompts that test cybersecurity knowledge in realistic security scenarios.
• Evaluate AI responses for quality, accuracy, and cybersecurity relevance.
• Use practical judgment from security engineering or offensive security work.
• Contribute independently in an asynchronous remote workflow.

• Schedule: 20+ hours per week with flexible participation.
• Language: Fluency in English.
• Experience: At least three years of professional experience in security engineering or offensive security.
• Relevant backgrounds include penetration testing, red teaming, malware analysis, threat hunting, threat intelligence, vulnerability research, and security consulting.
• Tools: Hands-on experience with one or more of Burp Suite, Nmap, Wireshark, Metasploit Framework, BloodHound, Impacket, Nessus, or Hashcat.
• Skills: Ability to write cybersecurity prompts and make informed judgments about AI-generated responses.