Agentic AI Security Engineer / AI Security Specialist

Wipro; Bengaluru; On-site; INR 3,500,000 - 5,500,000; Full time

Job summary

Wipro is seeking an experienced Agentic AI Security Engineer in Bengaluru to secure next-generation AI systems, including LLMs, AI agents, and multi-agent ecosystems. You will identify attack vectors, implement guardrails, and conduct adversarial testing across the AI lifecycle.

Responsibilities include designing secure architectures, performing threat modeling, and leading AI red-teaming efforts while shaping AI governance and data protection controls within enterprise environments.

Qualifications

• 8–10 years of security engineering/AI security experience.
• Strong knowledge of LLM security and prompt manipulation risks.
• Experience with threat modeling and red-teaming in AI systems.
• Familiarity with governance, risk, and compliance for AI.

Responsibilities

• Design security architectures for Agentic AI and autonomous systems.
• Conduct AI threat modeling and attack path analysis.
• Perform AI red teaming and penetration testing of AI workflows.
• Develop AI governance policies and guardrails.

Skills

AI security

LLM security

Red team

Governance

Tools

MITRE ATLAS

MITRE ATTACK

OWASP Top 10

Job description

Job Description: Agentic AI Security Engineer / AI Security Specialist

Role Overview

We are seeking a highly skilled Agentic AI Security Engineer to secure next-generation AI systems, including Large Language Models (LLMs), AI Agents, multi-agent ecosystems, and autonomous decision‑making platforms. The ideal candidate will possess expertise in AI security engineering, LLM security, AI red teaming, governance frameworks, and security data science to help build, assess, and protect enterprise AI solutions.

This role will be responsible for identifying AI-specific attack vectors, implementing security controls and guardrails, conducting adversarial testing, and establishing governance practices across the AI lifecycle.

Key Responsibilities

Agentic AI Security Engineering

• Design and implement security architectures for Agentic AI and autonomous AI systems.
• Assess security risks associated with AI agents, multi-agent orchestration, tool usage, and autonomous decision‑making workflows.
• Define and implement security controls for AI agents interacting with enterprise applications, APIs, and external systems.
• Conduct AI threat modeling and attack path analysis for agent-based architectures.

LLM & Model Security

• Secure Large Language Models (LLMs), Foundation Models, and Generative AI solutions.
• Evaluate model vulnerabilities, adversarial attack surfaces, and prompt-based exploitation techniques.
• Implement controls against:
  • Prompt Injection
  • Jailbreak Attacks
  • Data Leakage
  • Model Poisoning
  • Model Extraction
  • Model Theft
  • Adversarial Manipulation
  • Hallucination Risks
• Assess security of Retrieval Augmented Generation (RAG) and AI Agent frameworks.

AI Red Teaming

• Conduct offensive security assessments against AI/ML and GenAI systems.
• Design adversarial attack scenarios targeting models, prompts, agents, and AI workflows.
• Perform AI penetration testing and control validation exercises.
• Leverage frameworks such as:
  • MITRE ATLAS
  • MITRE ATT&CK
  • OWASP Top 10 for LLM Applications

AI Governance & Guardrails

• Develop and implement AI governance frameworks and security policies.
• Establish responsible AI controls and risk management practices.
• Define and manage:
  • Prompt Guardrails
  • Content Moderation
  • Data Protection Controls
  • Human-in-the-Loop Approvals
  • Model Access Controls
  • AI Risk Monitoring
• Support compliance with enterprise AI governance standards and regulatory requirements.

Security Data Science

• Apply data science and machine learning techniques to solve cybersecurity challenges.
• Analyze AI-related security telemetry and threat intelligence datasets.
• Develop predictive models and anomaly detection capabilities.
• Evaluate model robustness, explainability, fairness, and resilience.
• Collaborate with SOC, Threat Intelligence, and Security Engineering teams to strengthen AI-driven security capabilities.

Mandatory Skills: Data Privacy.

Experience: 8-10 Years.

Reinvent your world. We are building a modern Wipro. We are an end-to-end digital transformation partner with the boldest ambitions. To realize them, we need people inspired by reinvention. Of yourself, your career, and your skills. We want to see the constant evolution of our business and our industry. It has always been in our DNA - as the world around us changes, so do we. Join a business powered by purpose and a place that empowers you to design your own reinvention.