Expected compensation: 70.00 USD Per Hour
HireArt is helping our client find a Cybersecurity SME, AI Red Team to apply offensive security expertise to evaluating AI models and coding agents for cybersecurity risks and unsafe capabilities.
In this role, you'll test AI models and coding agents in sandboxed environments to identify vulnerabilities and assess their ability to generate harmful offensive cyber tools. You'll evaluate findings against established safety specifications, develop testing methodologies, and provide actionable recommendations to engineering and safety teams. The role will also expand into agent and harness red-teaming as evaluation capabilities evolve.
The ideal candidate has strong offensive security experience, hands-on knowledge of exploit development and malware, and an understanding of AI models and agents. They're analytical, creative, and skilled at evaluating technical risks, documenting findings, and communicating complex security issues across teams.
As a Cybersecurity SME, AI Red Team , You'll
- Red-team AI coding agents in sandboxed environments, using iterative testing techniques to evaluate whether models can generate offensive tools, including exploits, malware, and attack tooling.
- Assess model outputs against safety specifications, determine violations and severity, and identify when further testing is needed.
- Define and refine criteria for unsafe capability uplift, identifying ambiguous cases and gaps in existing safety specifications.
- Evaluate model capabilities in vulnerability discovery, exploit development, and malware analysis, verifying whether generated tools function as intended.
- Investigate agent-specific vulnerabilities, including prompt injection, tool misuse, and privilege escalation, as testing expands to agent and harness environments.
- Develop realistic attack scenarios and evaluation datasets, reviewing expert-written prompts and model outputs for technical accuracy.
- Document security findings, including severity, reproduction steps, and recommended mitigations, and communicate results to engineering and safety teams.
- Map findings to established frameworks, including MITRE ATLAS, OWASP Top 10 for LLM Applications, and NIST AI Risk Management Framework (AI RMF).
- Train and mentor red teamers and annotators on cybersecurity concepts while staying current on emerging AI attack techniques.
Requirements
- 2+ years of offensive security experience in penetration testing, red teaming, vulnerability research, or exploit development
- Hands-on experience with offensive security techniques, including exploit development, malware, post-exploitation, and web or cloud attacks
- Scripting proficiency, preferably Python, with the ability to assess the functionality of AI-generated offensive tools
- Working knowledge of large language models (LLMs), AI agents, and common attack techniques targeting these systems
- Strong written communication skills, with the ability to explain technical security risks to researchers, engineers, and executives
- Ability to handle sensitive or potentially disturbing content responsibly while following confidentiality and information-handling protocols
- Must be a U.S. citizen
Preferred Qualifications
- Recognized security certifications or demonstrated expertise through OSCP, OSEP, GPEN, published CVEs, CTF results, or bug bounty achievements
- Experience in AI/ML security, adversarial machine learning, or model evaluation
- Experience in government, defense, intelligence, or critical infrastructure security
- Background in malware reverse engineering, cloud security (AWS, GCP, Azure), or secure software development
- Conference presentations, published research, or contributions to open-source security tools
Benefits
- 96 hours of PTO accrued per year at a rate of 1 hour for every 20 hours worked
- 13 paid holidays
- Pre-tax commuter benefits
- Employer (HireArt) Subsidized healthcare benefits
- Flexible Spending Account for healthcare-related costs
- HireArt covers all costs for short and long-term disability and life insurance
- 401k package
Commitment
This is a full-time, ongoing contract position staffed via HireArt. The role is remote and open to U.S.-based candidates. Candidates local to the Dallas, TX area will be required to work a hybrid schedule out of the Southlake office.
HireArt values diversity and is an Equal Opportunity Employer. We are interested in every qualified candidate who is eligible to work in the United States. Unfortunately, we are not able to sponsor visas or employ corp-to-corp.