AI Engineer - Cyber Programs
The Coca-Cola Company6 days ago
Atlanta, GA, USASenior / Staff+
Base Salary
$152k - $178k/yr
Responsibilities
- Plan and execute adversarial testing engagements against AI models, LLM applications, agentic AI systems, and AI infrastructure.
- Test for prompt injection, jailbreaking, output manipulation, data poisoning, model inversion, training-data extraction, membership inference, and adversarial evasion.
- Evaluate AI architectures, model hosting, API exposure, data pipelines, fine-tuning workflows, retrieval-augmented generation, agent tool-use chains, and third-party AI components.
- Develop AI red-team methodologies, playbooks, testing frameworks, custom tooling, scripts, and automation.
- Evaluate AI security controls, human oversight, governance processes, monitoring, logging, incident response readiness, and remediation measures.
- Coordinate with external consultants, specialized AI security firms, bug bounty programs, AI governance teams, development teams, and business units.
- Produce adversarial testing reports with findings, evidence, risk ratings, and remediation guidance, and brief Cyber Defense leadership and the CISO.
Requirements
- 8–12 years of progressive cybersecurity experience, including 3–5 years focused on AI/ML security, AI adversarial testing, or applied AI research with a security focus.
- Hands-on experience adversarially testing large language models, machine learning models, agentic AI, or AI-enabled applications.
- Strong understanding of AI/ML systems, model architectures, training pipelines, inference APIs, fine-tuning, retrieval-augmented generation, and agentic frameworks.
- Knowledge of AI-specific attack techniques such as prompt injection, jailbreaking, data poisoning, model inversion, training-data extraction, and adversarial evasion.
- Familiarity with NIST AI RMF, MITRE ATLAS, OWASP Top 10 for LLMs, and ISO/IEC 42001.
- Experience with AI adversarial testing tools such as Garak and PyRIT, plus the ability to develop custom testing tooling.
- Offensive security experience in penetration testing, red teaming, or vulnerability research applied to AI contexts.
- Proficiency in Python and familiarity with PyTorch, TensorFlow, or equivalent ML frameworks.
- Strong written and verbal communication skills for technical and executive audiences.
- Bachelor’s degree in Computer Science, Cybersecurity, Data Science, Engineering, or a related technical field required; a master’s degree or advanced research experience is highly desirable.
- Relevant certifications such as OSCP, GIAC, CISSP, or AI-specific credentials are a plus.
Benefits
- Annual base pay range is $152,000–$178,300, varying by geography, knowledge, skills, and experience.
- Benefits may include medical, financial, and other position-dependent benefits.
- Annual incentive reference value is 15%.
- The position is based in Atlanta, United States, with 00%–25% travel required and no relocation provided.
- The Coca-Cola Company does not offer employment-based visa sponsorship for this position.