Coca-Cola
AI Engineer - Cyber Programs
US - GA - Atlanta · 1d ago
Citizen / GC only8+ YOE
Quick summary
AI parsed- Experience
- 8-12 years cybersecurity with 3-5 years AI/ML security, adversarial testing of AI systems. Key skills: prompt injection testing, jailbreaking, data poisoning, model inversion, NIST AI RMF, MITRE ATLAS, OWASP Top 10 for LLMs, Garak, PyRIT, Python, PyTorch, TensorFlow, penetration testing, red teaming
- Salary
- $152,000 - $178,300 USD
- Arrangement
- onsite
Responsibilities
- Plan and execute adversarial testing engagements against the Company's AI models, LLM-based applications, agentic AI systems, and AI infrastructure for vulnerabilities including prompt injection, jailbreaking, and data poisoning
- Develop and maintain AI red team methodologies, playbooks, testing frameworks aligned with NIST AI RMF, MITRE ATLAS, and OWASP Top 10, and build custom tooling for adversarial testing
- Assess effectiveness of AI security controls including input/output filtering, content moderation, guardrails, and human oversight mechanisms; recommend proportionate mitigations
- Produce clear adversarial testing reports with findings, risk ratings, and remediation guidance; maintain knowledge base of AI vulnerabilities and brief leadership on AI security posture
Benefits
Full range of medical benefits · Financial benefits · 15% annual incentive reference value
Full description
Job Description Summary:
Overview
The AI Engineer - Cyber Programs is The Coca-Cola Company's dedicated adversarial testing specialist for AI systems. This role systematically probes the Company's AI models, AI-enabled applications, and AI infrastructure for vulnerabilities, ensuring that AI deployments across the enterprise are resilient against adversarial manipulation, misuse, and emerging attack techniques. The focus is on AI-specific adversarial testing — not traditional network or application penetration testing — covering risks such as prompt injection, jailbreaking, data poisoning,…