SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Handshake AI is seeking a Cybersecurity Red Teamer to evaluate whether AI models can be manipulated into generating functional malware, exploit code, attack tooling, or operational guidance that could assist threat actors in cyberattacks. You will think like an attacker with access to a highly capable AI assistant, crafting adversarial prompts and multi-turn interaction chains that simulate how real threat actors—from inexperienced attackers to advanced persistent threat operators—might use LLMs to accelerate reconnaissance, weaponization, exploitation, lateral movement, persistence, and exfiltration.
Your core responsibility is to find gaps between what a model's safety guardrails are intended to block and what a skilled adversary can actually extract. You will design technically grounded adversarial prompts testing whether models provide meaningful assistance across the cyber kill chain. You'll evaluate model-generated code and technical output for functional correctness, determining whether outputs represent real exploits, plausible attack tooling, or nonfunctional noise.
Key activities include testing model behavior across offensive categories (malware generation, vulnerability exploitation, social engineering, credential harvesting, privilege escalation, command-and-control infrastructure, data exfiltration), probing dual-use boundaries, simulating attacker personas at varying skill levels, testing multi-step and multi-turn attack chains, and scoring model responses using structured harm taxonomies and severity rubrics calibrated to real-world exploitability.
You will document findings with clear technical reasoning, contribute to the development of cybersecurity-specific evaluation frameworks, collaborate with red teamers and AI researchers, and stay current on evolving tactics, techniques, procedures, CVEs, and jailbreak techniques.
Required qualifications include professional experience in offensive security, penetration testing, red teaming, vulnerability research, malware analysis, threat intelligence, or incident response. You must be able to read, write, and evaluate code in languages commonly used for offensive tooling (Python, PowerShell, Bash, C/C++, JavaScript), understand common attack frameworks and MITRE ATT&CK, assess functional correctness of model-generated technical output, and have hands-on experience with multiple LLMs. Strong ethical judgment and the ability to separate adversarial thinking from personal values are essential.
