Senior QA Analyst / Tester

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Senior QA Analyst / Tester based in United States.

The Senior QA Analyst / Tester will play a critical role in identifying vulnerabilities and security risks across advanced AI systems.
You will design and execute adversarial testing campaigns across large language models, multimodal systems, and autonomous agents.
The role combines AI security, offensive testing, red teaming, software engineering, and quality assurance in a highly technical environment.
You will investigate attack vectors, prompt injection techniques, jailbreaks, harmful outputs, and other unintended model behaviors.
Working closely with security, development, and engineering teams, you will turn testing findings into actionable remediation recommendations.
You will also help strengthen evaluation frameworks, adversarial datasets, benchmarks, and standardized testing processes as AI threats continue to evolve.
This is an opportunity for an experienced security professional to make a direct impact on the reliability, safety, and resilience of emerging AI technologies.

• 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.

We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team.

We appreciate your interest and wish you the best!

Why Apply Through Jobgether?

Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time.

#LI-CL1