1 hour ago
Bengaluru, IndiaSenior
Responsibilities
- Develop and maintain security and resilience for enterprise-grade AI and Generative AI services.
- Secure LLMs, agentic AI systems, multi-agent workflows, inference services, fine-tuning pipelines, and runtime execution environments.
- Implement security controls for Model Context Protocol and related agent integration patterns.
- Manage AI platform security across public cloud AI services, self-hosted models, and third-party AI providers.
- Build automated Python and policy-as-code security guardrails for access control, data protection, model usage limits, and runtime monitoring.
- Partner with AI Platform, Cloud Platform, DevOps, Software Engineering, and Compliance teams to embed security into the AI development lifecycle.
- Perform threat modeling and risk assessments for AI architectures, including RAG pipelines, vector databases, agent frameworks, and model supply chains.
- Support investigation, containment, remediation, and lessons learned for AI-related security incidents.
- Contribute to enterprise AI security standards, reference architectures, and best practices.
- Mentor junior engineers and serve as a senior technical voice across engineering and leadership teams.
Requirements
- Bachelor’s or Master’s degree in Computer Science, Cybersecurity, Artificial Intelligence/Machine Learning, or a related field.
- At least 6 years of cybersecurity engineering experience with ownership of complex, enterprise-scale systems.
- Demonstrated experience addressing security challenges involving LLMs, Generative AI, or agentic AI systems, including model misuse, prompt injection, hallucination risk, and data governance.
- Strong understanding of cloud security across AWS, Azure, and/or GCP, including IAM, networking, encryption, logging, and monitoring.
- Hands-on Python experience and security automation for scalable AI security control enforcement.
- Experience securing containerized and distributed systems, including Kubernetes and service meshes.
- Familiarity with model registries, vector databases, RAG pipelines, fine-tuning workflows, and inference gateways.
Categories
