This is a high-impact IC role reporting to the Exposure Management engineering leadership. You will influence strategy, mentor senior engineers, and ship production systems used by the largest enterprises in the world.
Responsibilities
Architect & Build Agentic Security Experiences
Design and implement Blue (investigate/triage), Green (remediate/harden), and Red (attack simulation) agents operating across customer environments.
Define agent architecture: planning, tool use (MCP skills), memory, context retrieval, and human-in-the-loop controls.
Build orchestration over the Security Graph, correlating exposure signals across cloud, device, identity, data, and AI.
Drive AI-Native Platform Design
Architect skill, knowledge, context, and memory layers for agentic security systems.
Design MCP-based skill interfaces for customization and extensibility.
Define how LLMs interact safely and accurately with structured security data (vulnerabilities, misconfigurations, attack paths, graph relationships).
Shape AI-for-Security Strategy
Partner with PMs and domain leads to define where AI autonomy vs. human involvement is needed.
Evaluate and integrate foundation models (Azure OpenAI, fine-tuned models) for tasks such as risk scoring, remediation planning, and blast radius analysis.
Stay ahead of industry solutions (Wiz AI-APP, CrowdStrike Charlotte AI, Palo Alto XSIAM).
Technical Leadership & Influence
Set technical direction across multiple teams (20-30 engineers).
Drive architecture decisions, design reviews, and engineering excellence.
Mentor senior engineers (L63-L65) and grow the AI-for-security discipline.
Represent the team across us (Security Copilot, MSG, Azure AI, Research).
Must Have
8+ years of software engineering experience, with 3+ years applying ML/AI to production systems.
Deep expertise in LLM application development, including prompt engineering, RAG, and agent frameworks such as AutoGen, Semantic Kernel, LangChain, or similar.
Strong systems design skills, including distributed cloud systems, streaming pipelines, graph databases, and API design at scale.
Experience building security products or working with security data such as vulnerabilities, misconfigurations, identity, and cloud posture.
Track record of driving ambiguous, cross-team technical initiatives from concept to production.
Preferred
Proficiency in Python and at least one systems language such as C, Go, Rust, or Java.
Experience with our Security stack including Defender, Sentinel, Entra, Purview, Intune, and MSEM.
Familiarity with MCP (Model Context Protocol) and tool-use patterns for LLM agents.
Background in security operations, red teaming, or exposure management.
Experience with knowledge graphs and graph-based reasoning for security.
Publications or patents in AI/ML applied to cybersecurity.
Experience with Azure OpenAI Service, Copilot extensibility, or Security Copilot skills development.
BS or MS in Computer Science, Engineering, or equivalent experience
