AI Red Teamer, Cybersecurity (Remote)

Handshake•Remote, Remote

5d•$65 - $125•Remote

About The Position

As a Cybersecurity Red Teamer, you will evaluate whether AI models can be manipulated into generating functional malware, viable exploit code, attack tooling, or step-by-step operational guidance that could give a threat actor meaningful assistance in carrying out cyberattacks. Your job is to find the gaps between what a model’s safety guardrails are intended to block and what a skilled adversary can actually extract. This role requires you to think like an attacker who has access to a highly capable AI assistant. You will craft adversarial prompts and multi-turn interaction chains that simulate how real threat actors, ranging from inexperienced attackers to advanced persistent threat operators, might use LLMs to accelerate reconnaissance, weaponization, exploitation, lateral movement, persistence, and exfiltration. You will then evaluate whether the model’s output is genuinely dangerous or merely surface-level noise. Deep cybersecurity expertise is essential. Your value will come from being able to examine a model-generated payload, exploit chain, or attack plan and determine whether it would actually work, how much refinement it would require, and what type of attacker it could meaningfully assist. This position may be performed from our Seattle location or remotely within the United States. Seattle-based and remote team members will collaborate closely through shared evaluation workflows, regular feedback, and virtual working sessions.

Requirements

Professional experience in offensive security, penetration testing, red teaming, vulnerability research, malware analysis, threat intelligence, or incident response
Ability to read, write, and evaluate code in languages commonly used for offensive tooling, such as Python, PowerShell, Bash, C/C++, or JavaScript
Understanding of common attack frameworks, techniques, and procedures, including MITRE ATT&CK and OWASP
Ability to assess the functional correctness and real-world exploitability of model-generated technical output
Strong hands-on experience using multiple LLMs, such as ChatGPT, Claude, Gemini, or open-source models
Creative and adversarial problem-solving skills
Clear and precise written communication, including the ability to explain technical risk to nonspecialist audiences
Strong ethical judgment and the ability to separate adversarial thinking from personal values
Ability to work independently while collaborating effectively in a feedback-heavy, distributed environment

Nice To Haves

Relevant certifications, such as OSCP, OSCE, GPEN, GXPN, CRTO, CRTL, CEH, or similar
Active or previous security clearance
Experience with exploit development, reverse engineering, or binary analysis
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

Responsibilities

Design technically grounded adversarial prompts that test whether models provide meaningful assistance across the cyber kill chain, from reconnaissance through exfiltration and impact
Evaluate model-generated code and technical output for functional correctness, determining whether outputs represent real exploits, plausible attack tooling, or nonfunctional noise
Test model behavior across offensive categories, including malware generation, vulnerability exploitation, social engineering, credential harvesting, privilege escalation, command-and-control infrastructure, and data exfiltration
Probe dual-use boundaries by testing how models respond to queries that combine legitimate security research, penetration testing, and defensive operations with offensive applications
Simulate attacker personas at varying skill levels, including opportunistic, intermediate, and advanced or APT-level actors
Test multi-step and multi-turn attack chains, including scenarios in which early turns establish benign context before pivoting to malicious requests
Score model responses using structured harm taxonomies and severity rubrics calibrated to real-world exploitability
Document findings with clear technical reasoning, including what a response gets right, what it gets wrong, and what level of attacker it could realistically assist
Contribute to the development and refinement of cybersecurity-specific evaluation frameworks and threat models
Collaborate with red teamers, AI researchers, and policy teams to translate findings into actionable model improvements
Stay current on evolving tactics, techniques, and procedures, CVEs, jailbreak techniques, and the intersection of AI and offensive security