Job
Description
Role Overview We are hiring a Technical Lead – AI Security to join our CISO team in Mumbai. This is a critical, hands-on role — ensuring the trustworthiness, resilience, and compliance of AI/ML systems, including large language models (LLMs). You will work at the intersection of cybersecurity and AI, shaping secure testing, understanding secure MLOps/LLMOps workflows, and leading technical implementation of defenses against emerging AI threats. This role requires both strategic vision and strong engineering depth. Key Responsibilities · Lead and operationalize the AI/ML and LLM security roadmap across training, validation, deployment, and runtime to enable AI Security Platform Approach. · Design and implement defenses against threats like adversarial attacks, data poisoning, model inversion, prompt injection, and fine-tuning exploits using industry leading open source and commercial tools. · Build hardened workflows for model security, integrity verification, and auditability in production AI environments. · Leverage AI security tools for scanning, fuzzing, and penetration testing models. · Apply best practices from OWASP Top 10 for ML/LLMs, MITRE ATLAS, NIST AI RMF, and ISO/IEC 42001 to test AI/ML assets. · Ensure AI model security testing framework aligns with internal policy, national regulatory requirements, and global best practices. · Plan and execute security tests for AI/LLM systems, including jailbreaking, RAG hardening, and bias/toxicity validation. Required Skills & Experience · 8+ years in cybersecurity, with at least 3+ years hands-on in AI/ML security or secure MLOps/LLMOps · Proficient in Python, TensorFlow/PyTorch, HuggingFace, LangChain, and common data science libraries · Deep understanding of adversarial ML/LLM, model evaluation under threat conditions, and inference/training-time attack vectors · Experience securing cloud-based AI workloads (AWS, Azure, or GCP) · Familiarity with secure DevOps and CI/CD practices · Strong understanding of AI-specific threat models (MITRE ATLAS) and security benchmarks (OWASP Top 10 for ML/LLMs) · Ability to communicate technical risk clearly to non-technical stakeholders · Ability to guide developers and data scientists to solve the AI Security risks. · Certifications: CISSP, OSCP, GCP ML Security, or relevant AI/ML certificates · Experience with AI security tools or platforms (e.g., model registries, lineage tracking, policy enforcement) · Experience with RAG, LLM-based agents, or agentic workflows · Experience in regulated sectors (finance, public sector) Show more Show less
