Sr AI Security & Testing Engineer

Job Title: Senior AI Security & Testing Engineer

Location: Remote

Duration: 12 Months

Position Overview:

As a Senior AI Security & Testing Engineer, you will serve as a technical authority responsible for securing, validating, and stress?testing enterprise AI systems. You will lead efforts across AI model testing, adversarial simulation, vulnerability management, penetration testing, and orchestration of AI tools within complex enterprise IT environments. This role blends deep security expertise with hands?on AI engineering, ensuring that AI?driven capabilities are safe, resilient, compliant, and seamlessly integrated into existing infrastructure.

Key Responsibilities:

AI Testing & Evaluation

• Design and execute comprehensive test strategies for AI/ML models, including functional testing, adversarial testing, red?teaming, hallucination detection, and model drift analysis.
• Build automated AI test harnesses and pipelines to validate model performance, reliability, and safety at scale.
• Evaluate LLMs, generative AI systems, and predictive models for robustness, bias, and misuse potential.

Vulnerability Management

• Identify, assess, and prioritize vulnerabilities across AI systems, APIs, data pipelines, and model deployment environments.
• Lead remediation planning with engineering, DevOps, and security teams.
• Maintain vulnerability dashboards, metrics, and reporting aligned with enterprise risk frameworks.
• Conduct threat modeling for AI systems, including model extraction, prompt injection, data poisoning, and supply?chain risks.

Simulation & Penetration Testing

• Develop and run simulation environments to test AI behavior under stress, adversarial conditions, and real?world attack scenarios.
• Perform penetration testing on AI?enabled applications, model endpoints, and orchestration layers.
• Create synthetic attack scenarios to evaluate system resilience and incident response readiness.
• Collaborate with red teams and blue teams to integrate AI?specific attack vectors into enterprise security exercises.

AI Tool Orchestration & Enterprise Integration

• Architect and implement integrations between AI tools, security platforms, and enterprise IT systems.
• Build workflows that connect AI models with monitoring, logging, SIEM, SOAR, and DevSecOps pipelines.
• Evaluate and integrate third?party AI security tools, model governance platforms, and testing frameworks.
• Ensure AI systems comply with enterprise architecture standards, data governance policies, and regulatory requirements.

Required Qualifications

• 7+ years in cybersecurity, penetration testing, or security engineering, with at least 2+ years focused on AI/ML systems.
• Strong proficiency in Python, security automation, and AI/ML testing frameworks.
• Hands?on experience with LLMs, vector databases, model deployment platforms, and MLOps pipelines.
• Deep understanding of adversarial ML, model vulnerabilities, and AI?specific threat landscapes.
• Expertise with vulnerability scanners, SAST/DAST tools, penetration testing suites, and cloud security platforms.
• Experience integrating AI systems with enterprise IT (APIs, microservices, identity systems, logging, monitoring, etc.).
• Familiarity with NIST AI RMF, OWASP Top 10 for LLMs, and emerging AI security standards.

Preferred Qualifications

• Experience with red?team operations or offensive security research.
• Background in building AI evaluation frameworks or automated testing systems.
• Certifications such as OSCP, OSWE, CEH, CISSP, or AI?focused credentials.
• Experience with Kubernetes, cloud?native architectures, and secure model deployment.
• Knowledge of data governance, privacy engineering, and secure data lifecycle management.