Job Description
Job Title: AI Security Engineer
Location: Mumbai | Work Type: Hybrid
Experience Required: 7+ years | Notice Period: 30–45 days
Role Overview
We are looking for an AI Security Engineer to secure AI/ML and Large Language Model (LLM)–based systems across their lifecycle. The role focuses on protecting AI models, data, pipelines, and integrations from emerging AI-specific threats while enabling safe and responsible AI adoption within the enterprise.
Key Responsibilities
• Secure LLMs, ML models, NLP systems, and deep learning pipelines
• Identify and mitigate AI risks including prompt injection, data leakage, model poisoning, hallucination misuse, and unauthorized model access
• Implement AI guardrails such as input/output validation, PII masking, and content filtering
• Deploy and manage LLM firewall / AI security tools (Giskard, AI Shield, Arthur Shield, or similar)
• Secure RAG pipelines, fine-tuning workflows, and agentic AI architectures
• Protect AI workloads on Azure AI Foundry and Azure OpenAI
• Govern usage of Hugging Face models/datasets and Microsoft Copilot
• Integrate AI security controls into CI/CD and MLOps pipelines
• Support AI risk assessments, audits, and regulatory compliance
Required Technical Skills
• Strong understanding of LLMs, ML, NLP, and deep learning
• Knowledge of OWASP Top 10 for LLMs and AI threat models
• Experience with Azure AI platforms, APIs, IAM, encryption, and logging
• Hands-on experience with AI security / LLM firewall tools
• Solid foundation in application security, cloud security, and DevSecOps
Nice to Have
• Experience in BFSI or regulated environments
• Exposure to Responsible AI, AI governance, or adversarial ML
Core Skills
Artificial Intelligence | Machine Learning | AIML | Cybersecurity
Interested Candidates Can Share Their Updated Resume On jeena.sunil@evokehr.com
Location: Mumbai | Work Type: Hybrid
Experience Required: 7+ years | Notice Period: 30–45 days
Role Overview
We are looking for an AI Security Engineer to secure AI/ML and Large Language Model (LLM)–based systems across their lifecycle. The role focuses on protecting AI models, data, pipelines, and integrations from emerging AI-specific threats while enabling safe and responsible AI adoption within the enterprise.
Key Responsibilities
• Secure LLMs, ML models, NLP systems, and deep learning pipelines
• Identify and mitigate AI risks including prompt injection, data leakage, model poisoning, hallucination misuse, and unauthorized model access
• Implement AI guardrails such as input/output validation, PII masking, and content filtering
• Deploy and manage LLM firewall / AI security tools (Giskard, AI Shield, Arthur Shield, or similar)
• Secure RAG pipelines, fine-tuning workflows, and agentic AI architectures
• Protect AI workloads on Azure AI Foundry and Azure OpenAI
• Govern usage of Hugging Face models/datasets and Microsoft Copilot
• Integrate AI security controls into CI/CD and MLOps pipelines
• Support AI risk assessments, audits, and regulatory compliance
Required Technical Skills
• Strong understanding of LLMs, ML, NLP, and deep learning
• Knowledge of OWASP Top 10 for LLMs and AI threat models
• Experience with Azure AI platforms, APIs, IAM, encryption, and logging
• Hands-on experience with AI security / LLM firewall tools
• Solid foundation in application security, cloud security, and DevSecOps
Nice to Have
• Experience in BFSI or regulated environments
• Exposure to Responsible AI, AI governance, or adversarial ML
Core Skills
Artificial Intelligence | Machine Learning | AIML | Cybersecurity
Interested Candidates Can Share Their Updated Resume On jeena.sunil@evokehr.com
💡 Quick Summary
Seeking a career-building opportunity? The AI Security Engineer position is now open for candidates interested in the IT Engineer & Developer Jobs sector. This role in Mumbai offers a professional environment and growth potential.
Requirement Snapshot: Candidates should possess basic communication skills, a proactive attitude, and the ability to work in a team. Experience in IT Engineer & Developer Jobs is a plus.