Senior Software Engineer, Security AI

Microsoft Microsoft · Big Tech · Redmond, WA +2 · Software Engineering

Senior Software Engineer to build AI-powered security systems for Cloud Security. This role involves designing, building, and operating production AI services that combine LLMs, RAG, agent-based workflows, and security data to solve real-world security challenges. The engineer will work on distributed systems, applied AI, cloud security, and responsible AI, focusing on improving detection, investigation, response, and risk reduction across Microsoft's cloud environment. The role requires owning technical components, driving implementation from design to operation, and continuous improvement using data and feedback. Collaboration with various teams is essential for delivering secure, operationally excellent, durable, and impactful systems.

What you'd actually do

  1. Design, build, test, and operate AI-powered services that support security engineering and security operations workflows.
  2. Develop AI-enabled workflows that help engineering and security teams analyze information, retrieve relevant context, summarize findings, and make faster, higher-quality decisions.
  3. Build scalable systems that use large language models, retrieval-augmented generation, embeddings, semantic search, knowledge graphs, and related AI techniques to support security scenarios.
  4. Implement evaluation, monitoring, and telemetry capabilities to measure AI system quality, reliability, performance, and safety.
  5. Partner with engineering, applied science, product, security operations, and other teams to translate AI advances into practical, secure, durable and reliable platform capabilities.

Skills

Required

  • Bachelor's Degree in Computer Science or related technical field AND 4+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python
  • Microsoft Cloud Background Check

Nice to have

  • Master’s degree or PhD in Computer Science, Machine Learning, Artificial Intelligence, or related technical field
  • Experience building multi-agent systems, tool-use frameworks, orchestration layers, autonomous workflows, or AI copilots in production environments.
  • Experience with vector databases, embeddings, semantic search, knowledge graphs, entity resolution, ranking, summarization, or context-grounding systems.
  • Experience with LLM evaluation, responsible AI, model safety, hallucination mitigation, prompt injection defense, model monitoring, or AI governance controls.
  • Experience with cloud security, security operations, threat detection, incident response, vulnerability management, identity and access systems, or security data platforms.
  • Experience with Azure services, Azure AI, Azure OpenAI, Microsoft Defender, Sentinel, Kusto, Kubernetes, or large-scale telemetry and analytics systems.
  • Demonstrated ability to drive technical solutions from design through production, influence engineering decisions within a team or project area, mentor peers, and deliver measurable customer or business impact.

What the JD emphasized

  • production AI systems
  • cloud scale
  • design through operation
  • continuously improving systems
  • secure by design
  • operationally excellent
  • durable
  • measurable platform impact
  • production environments
  • LLM evaluation
  • responsible AI
  • model safety
  • hallucination mitigation
  • prompt injection defense
  • model monitoring
  • AI governance controls
  • cloud security
  • security operations
  • threat detection
  • incident response
  • vulnerability management
  • identity and access systems
  • security data platforms

Other signals

  • AI-powered security systems
  • large language models
  • retrieval-augmented generation
  • agent-based workflows
  • security data