AI Red Teamer (Cybersecurity)

Join our team as a Cybersecurity Red Teamer, where you will evaluate the potential for AI models to be manipulated into generating functional malware and viable exploit code. You will think like an attacker with access to a highly capable AI assistant, crafting adversarial prompts and simulating real threat actor scenarios. Your deep cybersecurity expertise will be essential in determining the effectiveness of model-generated outputs and contributing to the development of cybersecurity evaluation frameworks. This position can be performed remotely within the United States or from our Seattle location.

You understand that the difference between a useful coding assistant and a dangerous one often comes down to context, specificity, and operational detail

You care about AI safety because you understand what can happen when powerful tools are used irresponsibly

Responsibilities

• Evaluar si los modelos de IA pueden ser manipulados para generar malware funcional, código de explotación viable o herramientas de ataque.
• Identificar las brechas entre lo que las medidas de seguridad de un modelo están destinadas a bloquear y lo que un adversario hábil puede extraer.
• Diseñar y probar prompts adversariales que simulen cómo los actores de amenazas pueden utilizar los modelos de IA para acelerar diversas etapas del ciclo de ataque cibernético.

Requirements

• Strong ethical judgment and the ability to separate adversarial thinking from personal values
• Ability to read, write, and evaluate code in languages commonly used for offensive tooling, such as Python, PowerShell, Bash, C/C++, or JavaScript
• Strong hands-on experience using multiple LLMs, such as ChatGPT, Claude, Gemini, or open-source models
• Understanding of common attack frameworks, techniques, and procedures, including MITRE ATT&CK and OWASP
• Professional experience in offensive security, penetration testing, red teaming, vulnerability research, malware analysis, threat intelligence, or incident response

Creative and adversarial problem-solving skills

• Ability to work independently while collaborating effectively in a feedback-heavy, distributed environment
• Clear and precise written communication, including the ability to explain technical risk to nonspecialist audiences
• Ability to assess the functional correctness and real-world exploitability of model-generated technical output
• Relevant certifications, such as OSCP, OSCE, GPEN, GXPN, CRTO, CRTL, CEH, or similar
• Experience with exploit development, reverse engineering, or binary analysis

Active or previous security clearance

• You have spent years breaking into systems and want to apply that mindset to testing AI models
• You can examine a model-generated reverse shell, phishing template, or privilege-escalation script and quickly determine whether it would work in a real environment
• You think in kill chains and attack graphs, not just individual prompts
• You closely follow the offensive-security community and stay current when new techniques emerge

Preferred

• Background in cloud security, container security, or infrastructure-as-code attack surfaces
• Familiarity with AI and machine-learning attack surfaces, including prompt injection, model extraction, training-data poisoning, and adversarial examples
• Experience building or operating command-and-control frameworks, custom implants, or offensive tooling
• A bug-bounty track record or published CVEs
• Previous work in trust and safety, content moderation, or AI evaluation
• Familiarity with LLM APIs or evaluation tooling

Benefits

• You can collaborate effectively with a team whether you are working from Seattle or remotely