AI Engineer - Cyber Programs

Experteer Overview In this senior role, you will lead AI adversarial testing efforts to harden Coca-Cola’s AI models, apps, and infrastructure. You’ll design and execute red-team style engagements, develop tooling and playbooks, and deliver actionable findings to enable secure AI deployments. You’ll collaborate with governance, development teams, and external experts to ensure comprehensive coverage. This position sits at the intersection of AI security and cybersecurity, driving resilient AI across the enterprise. Compensation / Benefits * Plan and execute adversarial testing against AI models, LLM-based apps, agentic AI systems, and AI infrastructure * Test for AI-specific vulnerabilities (prompt injection, jailbreaking, data poisoning, model inversion, training data extraction) and evaluate architectures and data pipelines * Develop and maintain AI red team methodologies, playbooks, and tooling aligned with NIST AI RMF, MITRE ATLAS, OWASP Top 10 for LLMs * Build and integrate custom testing tooling and automate vulnerability scanning of AI systems * Assess effectiveness of AI security controls, governance processes, and incident response readiness * Coordinate with external consultants, AI security firms, and bug bounty programs * Produce clear, actionable adversarial testing reports for technical and executive audiences * Maintain a knowledge base of AI vulnerabilities and testing results to track remediation progress * Brief Cyber Defense leadership and the CISO on AI threat trends and security posture * Collaborate with governance, development teams, and business units to align testing with deployment roadmap Tasks * 8-12 years in cybersecurity, with 3-5 years in AI/ML security, adversarial testing of AI systems, or applied AI research with security focus * Hands-on experience with adversarial testing of AI systems (LLMs, ML models, agentic AI, AI-enabled apps) * Strong understanding of AI/ML architectures, training pipelines, inference APIs, fine-tuning, RAG, and agentic frameworks * Knowledge of AI-specific attack techniques (prompt injection, jailbreaking, data poisoning, model inversion, data extraction, evasion) * Familiarity with AI security frameworks (NIST AI RMF, MITRE ATLAS, OWASP Top 10 for LLMs, ISO/IEC 42001) * Experience with AI adversarial testing tools (Garak, PyRIT) and developing custom tooling * Offensive security fundamentals (penetration testing, red teaming, vulnerability research in AI contexts) * Excellent written and verbal communication for technical and executive audiences * Python programming; familiarity with ML frameworks (PyTorch, TensorFlow) * AI security certifications a plus (OSCP, GIAC, CISSP) * Bachelor’s degree in CS, Cybersecurity, Data Science, Engineering; Master’s desirable Key requirements * medical benefits * financial benefits * annual incentive program * full-time role * competitive base pay * opportunity to influence AI security posture

testing tooling and automate vulnerability scanning of AI systems * Assess effectiveness of AI security controls, governance processes, and incident response readiness * Coordinate with external consultants, AI security firms, and bug bounty programs * Produce clear, actionable adversarial testing reports for technical and executive audiences * Maintain a knowledge base of AI vulnerabilities and testing results to track remediation progress * Brief Cyber Defense leadership and the CISO on AI threat trends and security posture * Collaborate with governance, development teams, and business units to align testing with deployment roadmap Tasks * 8-12 years in cybersecurity, with 3-5 years in AI/ML security, adversarial testing of AI systems, or applied AI research with security focus * Hands-on experience with adversarial testing of AI systems (LLMs, ML models, agentic AI, AI-enabled apps) * Strong understanding of AI/ML architectures, training pipelines, inference APIs, fine-tuning, RAG, and agentic frameworks * Knowledge of AI-specific attack techniques (prompt injection, jailbreaking, data poisoning, model inversion, data extraction, evasion) * Familiarity with AI security frameworks (NIST AI RMF, MITRE ATLAS, OWASP Top 10 for LLMs, ISO/IEC 42001) * Experience with AI adversarial testing tools (Garak, PyRIT) and developing custom tooling * Offensive security fundamentals (penetration testing, red teaming, vulnerability research in AI contexts) * Excellent written and verbal communication for technical and executive audiences * Python programming; familiarity with ML frameworks (PyTorch, TensorFlow) * AI security certifications a plus (OSCP, GIAC, CISSP) * Bachelor’s degree in CS, Cybersecurity, Data Science, Engineering; Master’s desirable Key requirements * medical benefits * financial benefits * annual incentive program * full-time role * competitive base pay * opportunity to influence AI security posture