AI Security Engineer
Description
Hiring: Senior AI Security Engineer – GenAI & LLM Security
Location: Hyderabad
Experience: 8+ Years
Relevant Experience: 4+ Years in AI
Hiring Priority: Immediate
Job Overview
We are looking for an experienced AI Security Engineer with strong expertise in Artificial Intelligence security, Generative AI, Large Language Models (LLMs), RAG architectures and enterprise application security.
The ideal candidate should have hands-on experience identifying and mitigating security vulnerabilities in LLM-based applications, implementing AI security guardrails, conducting AI red teaming and securing Agentic AI systems.
The candidate will be responsible for ensuring the security, privacy, reliability and compliance of enterprise-grade AI applications.
Key Responsibilities
- Design and implement security frameworks for Generative AI and LLM-based applications.
- Conduct security assessments, vulnerability testing and penetration testing of LLM applications and RAG pipelines.
- Identify and mitigate prompt injection, jailbreak attacks, data leakage, data poisoning and adversarial attacks.
- Perform AI red teaming and security testing of AI-powered applications.
- Secure RAG architectures, vector databases, embeddings and enterprise knowledge repositories.
- Implement AI safety guardrails, input validation, output filtering and content moderation.
- Secure AI Agents, Multi-Agent Systems, tool calling, function calling and external API integrations.
- Evaluate security risks associated with MCP servers, tools and Agent-to-Agent communication.
- Implement authentication, authorization, RBAC, API security and access control mechanisms.
- Protect sensitive information through encryption, data masking and secure data handling.
- Perform threat modeling and risk assessments for AI/LLM applications.
- Establish AI security policies, governance standards and vulnerability remediation processes.
- Collaborate with AI Engineers, DevSecOps, Cloud Security and Cybersecurity teams.
- Monitor emerging AI security threats and continuously improve security controls.
Mandatory Technical Skills
- 8+ years of overall software industry experience.
- Minimum 4+ years of hands-on experience in AI, Generative AI, LLMs and RAG.
- Strong understanding of AI application security and secure software development.
- Hands-on experience securing LLM-powered applications and RAG architectures.
- Strong knowledge of OWASP Top 10 for LLM Applications.
- Experience identifying and mitigating prompt injection and jailbreak vulnerabilities.
- Experience with AI red teaming, adversarial testing and LLM security assessments.
- Strong Python programming and REST API security knowledge.
- Understanding of embeddings, vector databases and RAG security.
- Experience with authentication, authorization, RBAC and API security.
- Knowledge of data privacy, encryption and sensitive data protection.
- Experience with vulnerability assessment and penetration testing.
- Understanding of cloud security across AWS, Azure or GCP.
- Knowledge of DevSecOps and secure CI/CD practices.
Skills
Sign in to read and join the discussion.