AI/ML Security Engineer GenAI & Prompt Injection

Role & responsibilities

1. Design, develop, and maintain security evaluation frameworks for ML, Generative AI, LLMs, and Agentic AI applications.
2. Identify, reproduce, analyze, and remediate prompt injection and indirect prompt injection vulnerabilities.
3. Develop automated security and adversarial tests to evaluate LLMs and AI agents against jailbreaks, data leakage, and unsafe behavior.
4. Assess AI applications for security, safety, accuracy, reliability, and performance.
5. Build and maintain AI/ML security metrics, monitoring systems, evaluation pipelines, and reporting capabilities.
6. Collaborate with AI/ML engineers, security teams, and product teams to develop AI threat models, security controls, and guardrails.
7. Investigate vulnerabilities and unexpected behavior across LLMs, AI agents, APIs, and supporting infrastructure.
8. Develop and implement mitigation strategies to prevent unauthorized data exposure, prompt manipulation, and unsafe AI tool execution.
9. Contribute to AI/ML infrastructure, API development, CI/CD pipelines, and security automation.
10. Write scalable, secure, maintainable, and efficient Python code following software engineering best practices.

Preferred candidate profile

• Candidates with 67 years of experience in ML Engineering, Software Engineering, AI Security, Application Security, or a related technical field.
• Strong hands-on programming experience in Python and secure software development.
• Practical experience working with Generative AI, LLMs, and/or Agentic AI applications.
• Good understanding of prompt injection, indirect prompt injection, jailbreaks, data leakage, and AI-specific security risks.
• Experience identifying vulnerabilities and implementing security controls for AI/ML applications.
• Strong understanding of APIs, distributed systems, databases, testing methodologies, and software engineering principles.
• Experience developing automated testing frameworks, evaluation pipelines, or security assessment tools.
• Knowledge of AI threat modeling, adversarial testing, AI red teaming, and vulnerability assessment is highly preferred.
• Experience with Git/GitHub, Agile/Scrum, CI/CD pipelines, and collaborative software development.
• Familiarity with cloud infrastructure and deployment technologies such as AWS, Docker, and Kubernetes is an added advantage.
• Experience with ML deployment, production infrastructure, data pipelines, and AI monitoring frameworks is preferred.
• Java or experience with additional programming languages is an advantage.
• A relevant advanced degree in Computer Science, AI/ML, Cybersecurity, or a related discipline is a plus.
• Comfortable working in the US time zone and collaborating with distributed engineering and security teams.