AI Red Teamer, Cybersecurity (Remote)

The role

You will evaluate whether AI models can be manipulated into generating functional malware, exploit code, or operational guidance for cyberattacks. You will design adversarial prompts and simulate attacker personas to test model safety guardrails.

What you will do

• Design technically grounded adversarial prompts to test the cyber kill chain
• Evaluate model-generated code and technical output for functional correctness
• Test model behavior across offensive categories like malware generation and social engineering
• Probe dual-use boundaries between security research and offensive applications
• Simulate attacker personas at varying skill levels
• Test multi-step and multi-turn attack chains
• Score model responses using structured harm taxonomies and severity rubrics
• Document findings with clear technical reasoning
• Contribute to the development of cybersecurity-specific evaluation frameworks
• Collaborate with red teamers, AI researchers, and policy teams

Required qualifications

• 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 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
• Strong ethical judgment
• Ability to work independently while collaborating effectively in a feedback-heavy, distributed environment

Nice to have

• 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

About the company

Handshake AI supports frontier AI labs by working on their most complex data challenges at scale. The company was founded on the belief that everyone deserves a path to a great career.