Senior QA Analyst / Tester

Accountabilities:

• • Design and execute comprehensive adversarial testing campaigns against AI systems, including large language models, multimodal systems, and autonomous agents.
  • Research attack vectors, prompt injection techniques, jailbreaks, and other methods for identifying AI model vulnerabilities and unintended behaviors.
  • Evaluate and implement AI security testing tools that can improve the detection and response time for AI-specific threats.
  • Conduct structured red team exercises that simulate real-world deployment scenarios, edge cases, and diverse attack conditions.
  • Systematically test AI models for bias, toxicity, misinformation, harmful outputs, and other risks across different contexts and demographics.
  • Execute standardized security tests and contribute to strengthening the overall security posture against emerging AI threats.
  • Create adversarial datasets, benchmarks, and evaluation methodologies to assess model robustness and resilience.
  • Collaborate with security operations, global security teams, developers, and other technical stakeholders to conduct red team exercises and validate findings.
  • Document vulnerabilities, testing results, risks, and remediation recommendations, communicating findings clearly to technical and non-technical stakeholders.
  • Develop and maintain testing procedures, process documentation, operational reports, and performance metrics supporting the AI Red Team function.
  • Work effectively across distributed teams, geographies, and time zones to coordinate testing activities and drive remediation.

  Requirements:

  • Minimum 5 years of experience in penetration testing, red team operations, offensive cybersecurity, or AI red teaming.
  • Bachelor’s degree or higher in Computer Science, Information Technology, Programming, Software Development, Artificial Intelligence, Cybersecurity, or a related discipline, or equivalent professional experience.
  • Demonstrated experience in AI red teaming, conventional red team operations, penetration testing, or offensive cyber operations.
  • Strong understanding of artificial intelligence, machine learning, software applications, cloud computing, networking, and cybersecurity concepts.
  • Hands-on experience with AI and security testing tools such as SPLX, Garak, TextAttack, PyRIT, Burp Suite, Metasploit, Nessus, Cobalt Strike, Mythic/C2, NMAP, sqlmap, or comparable technologies.
  • Strong knowledge of web application technologies and Layer 7 protocols, including HTTP, DNS, and FTP.
  • Technical understanding of Generative AI, Agentic AI, A2A, MCP, or related emerging AI architectures and protocols.
  • Programming or scripting proficiency in languages such as Python, Ruby, Go, C++, PowerShell, Bash, or comparable languages.
  • Strong analytical and problem-solving skills, with the ability to investigate complex technical behaviors and identify meaningful security risks.
  • Excellent written and verbal communication skills, with the ability to translate technical vulnerabilities into clear findings and actionable recommendations.
  • Strong stakeholder management skills and the ability to collaborate effectively with globally distributed technical teams.
  • Relevant certifications such as OSCP, GPEN, GPXN, AI-focused red team certifications, AISEC+, GASAE, GOAA, OSAI+, or similar industry credentials are desirable.

  Benefits:

  • Fully remote opportunity within the United States.
  • Opportunity to work at the intersection of cybersecurity, quality assurance, and rapidly evolving AI technologies.
  • Exposure to advanced AI models, adversarial testing methodologies, and emerging AI security threats.
  • Opportunity to collaborate with global security, engineering, and development teams.
  • Meaningful opportunity to influence AI security practices, testing standards, and risk mitigation strategies.
  • Professional growth through hands-on work with modern AI security and offensive testing tools.
  • Inclusive and equal-opportunity work environment.
  • Potential for career development in AI security, red teaming, cybersecurity, and technology consulting.