Role : AI Security Engineer

We are looking for an experienced AI Security Engineer with 5+ years of experience in cybersecurity, AI/ML security, cloud security, or related domains.

The ideal candidate will have strong expertise in securing Generative AI, LLMs, Agentic AI, and ML platforms, with hands-on experience in GCP, Vertex AI, and GKE. The candidate will be responsible for identifying and mitigating security risks across AI/ML systems, performing AI threat modeling and red teaming, and implementing security controls for enterprise-scale GenAI solutions.

Key Responsibilities :

- Design and implement security controls for AI/ML, GenAI, LLM, and Agentic AI workloads.

- Perform AI/ML threat modeling, risk assessments, vulnerability assessments, and AI red teaming.

- Identify and mitigate threats including prompt injection, jailbreaks, data poisoning, model theft/extraction, adversarial attacks, and sensitive data leakage.

- Secure LLM applications, RAG pipelines, AI agents, vector databases, APIs, and model-serving infrastructure.

- Implement security best practices across GCP, Vertex AI, and GKE environments.

- Secure enterprise GenAI solutions including Gemini and Gemini Enterprise environments.

- Design and implement IAM, DLP, data privacy, encryption, access controls, and security monitoring for AI workloads.

- Assess AI models and applications for security, privacy, and compliance risks.

- Develop security frameworks and guardrails for Agentic AI systems, including agent-to-agent communication, tool usage, permissions, and autonomous actions.

- Monitor AI environments for anomalous behavior, unauthorized access, data exfiltration, and model abuse.

- Collaborate with ML engineers, data scientists, cloud engineers, developers, and security teams to integrate security throughout the AI/ML lifecycle.

- Define secure architecture and deployment patterns for production-grade LLM and GenAI applications.

- Conduct security reviews of AI models, prompts, datasets, APIs, and third-party AI services.

- Stay updated on emerging AI security threats, adversarial ML techniques, LLM vulnerabilities, and industry security frameworks.

Required Skills :

- 5+ years of experience in Cybersecurity, Cloud Security, AI/ML Security, Application Security, or related fields.

- Strong understanding of AI/ML security and adversarial machine learning.

- Hands-on experience with GenAI / LLM security.

- Strong experience with GCP, Vertex AI, and GKE.

- Experience securing Gemini / Gemini Enterprise or enterprise GenAI environments.

- Strong knowledge of AI threat modeling and AI red teaming.

- Understanding of Prompt Injection, Data Poisoning, Model Theft/Extraction, Jailbreaking, and Adversarial Attacks.

- Experience implementing DLP, IAM, data privacy, encryption, and security monitoring.

- Strong understanding of Agentic AI security, including agent permissions, tool access, identity, and data protection.

- Experience securing production LLM applications and AI/ML pipelines.

- Knowledge of cloud-native security principles and Kubernetes security.

- Strong analytical, problem-solving, and communication skills.

Preferred Skills :

- Google Professional Cloud Security Engineer certification.

- Google Professional Machine Learning Engineer certification.

- Experience with production-grade LLM security implementations.

- Knowledge of AI security frameworks such as OWASP Top 10 for LLM Applications, MITRE ATLAS, and NIST AI Risk Management Framework.

- Experience with AI security testing tools, model evaluation frameworks, and automated security testing.

- Exposure to regulatory requirements related to AI governance, data privacy, and responsible AI.

Education :

- Bachelors or Masters degree in Computer Science, Cybersecurity, Information Technology, AI/ML, or a related field.