Microsoft Security aspires to make the world a safer place by reshaping security and empowering users, customers, and developers with a security cloud that protects them with end-to-end, simplified solutions. This role aims to design and build GenAI-powered Security Agents to help enterprise customers understand, investigate, and mitigate identity risks across Entra ID.
Requirements
- 2+ years of hands-on experience building and deploying production-grade AI systems using Python, PyTorch, or TensorFlow.
- Proficiency in large language models (LLMs), embeddings, vector databases, and retrieval-augmented generation (RAG) architectures.
- Understanding of identity and security concepts, including authentication, access control, detection signals, and risk-based decisioning.
- Experience with prompt engineering, tool-augmented reasoning, and multi-agent frameworks for autonomous or task-oriented AI workflows.
- Experience with Azure AI Foundry, OpenAI APIs, or Semantic Kernel for enterprise-scale AI development.
- Familiarity with Microsoft Security offerings, such as Entra ID, Microsoft Defender, MDE, or MDI, and their associated risk and protection ecosystems.
- Knowledge of MCP (Model Context Protocol) or other interoperable agent architectures for secure model orchestration.
Responsibilities
- Design and build GenAI-powered Security Agents that enable enterprise customers to understand, investigate, and mitigate identity risks across Entra ID — including Identity Protection, Conditional Access, and related products.
- Reimagine and modernize traditional security workflows (e.g., detection development, validation, triage, and investigation) through intelligent automation, multi-agent orchestration, and reasoning-driven LLM systems.
- Develop secure, scalable AI pipelines and MCP-based services that integrate identity signals, risk data, and detection outputs across the broader Microsoft Security ecosystem.
- Prototype, evaluate, and deploy advanced agentic capabilities — such as retrieval-augmented generation (RAG), multi-agent framework, MCP servers, context engineering, and long-term agent memory — to support next-generation GenAI security agents.
- Collaborate with Microsoft Research and partner teams to drive model and signal exchange through the Agent-to-Agent (A2A) framework, enabling unified, cross-product intelligence for security-focused AI agents across Microsoft Security.
Other
- Ability to meet Microsoft, customer and/or government security screening requirements are required for this role.
- Microsoft Cloud Background Check: This position will be required to pass the Microsoft background and Microsoft Cloud background check upon hire/transfer and every two years thereafter.
