• 8+ years of relevant professional experience in cybersecurity, AI security, or related fields.
• Strong experience in AI security engineering, including securing AI/ML lifecycle components.
• Deep understanding of AI/ML lifecycle security risks and mitigation strategies.
• Hands-on experience with securing LLMs, foundation models, and Generative AI applications.
• Proficiency in AI red teaming, threat modeling, vulnerability assessment, and security testing.
• Knowledge of prompt injection, jailbreaks, adversarial attacks, and AI attack techniques.
• Experience with secure model development, training, deployment, and evaluation.
• Familiarity with DevSecOps practices and secure CI/CD pipelines.
• Strong scripting, automation skills, and experience with cloud security platforms such as AWS, Azure, or Google Cloud.
• Excellent analytical, problem-solving, and stakeholder management capabilities.

Responsibilities

The AI Security Engineer will be responsible for a broad range of security initiatives, including but not limited to:

• Performing comprehensive security assessments and threat modeling for AI, ML, Generative AI, and LLM-based solutions to identify vulnerabilities and develop mitigation strategies.
• Designing, implementing, and maintaining AI security controls, guardrails, and monitoring capabilities to detect and prevent malicious activities.
• Conducting AI red-team exercises, including prompt injection tests, jailbreak attempts, model manipulation, data leakage, and adversarial attack simulations.
• Securing the entire AI model lifecycle, from development and training to deployment and operational management, ensuring compliance with security standards.
• Embedding security controls within AI CI/CD pipelines and configuration management processes to promote secure development practices.
• Collaborating with cross-functional teams to define AI security standards, control requirements, and governance frameworks aligned with enterprise policies.
• Analyzing emerging AI threats and continuously improving defensive controls, testing methodologies, and security protocols.
• Supporting the responsible and secure adoption of AI technologies across enterprise environments, ensuring compliance with regulatory and ethical standards.

Benefits

Vbeyond offers a comprehensive benefits package designed to support our employees' professional growth and personal well-being. Our benefits include competitive salary packages, health insurance coverage, and retirement plans. We also provide opportunities for continuous learning and development through certifications, training programs, and industry conferences. Employees enjoy a flexible work environment that promotes work-life balance, along with a collaborative and inclusive culture that values innovation and diversity. Additionally, Vbeyond offers performance-based incentives and recognition programs to motivate and reward excellence in performance.

Equal Opportunity

Vbeyond is an equal opportunity employer committed to fostering an inclusive environment for all employees. We do not discriminate based on race, ethnicity, gender, age, religion, disability, sexual orientation, or any other protected characteristic. We believe in creating a diverse workforce that reflects the communities we serve and promotes innovation through varied perspectives. All qualified applicants will receive consideration for employment without regard to any protected status, and we are dedicated to providing a workplace free from discrimination and harassment.