Principal Software Engineer

Microsoft Microsoft · Big Tech · Redmond, WA +1 · Software Engineering

Principal Software Engineer to lead the architecture, design, operation, and evolution of an AI-driven, end-to-end autonomous support platform. This role focuses on complex agentic systems, including orchestration, grounding, evals, and observability, ensuring production-readiness, trustworthiness, and scalability for Microsoft's next-generation support experience.

What you'd actually do

  1. Lead system architecture and design for the complex, often ambiguous agentic support platform, using frameworks such as Azure AI Foundry, Microsoft Copilot Studio, or equivalents, while defining the patterns and SDK surfaces other engineers rely on.
  2. Owning the architecture and run-state reliability of AI-driven support workflows; defining the reliability bar for incident response and live-site health; and serving as a designated responsible individual (DRI) who leads incident retrospectives to identify root causes, owns repair actions, and prevents recurrence across the platform.
  3. Driving the design patterns that adapt AI workflows to changing support business policies and operational processes (e.g., SLA calculations, case ownership, escalation models).
  4. Driving customer trust, satisfaction, and sentiment, ensuring AI agents correctly understand intent and guide customers to resolution without degrading experience.
  5. Providing thought leadership on the security, privacy, and Responsible AI architecture—including rethinking role-based access control (RBAC), data access, case ownership vs. processing, and data exposure—and assuring visible compliance evidence (e.g., audit trails) across products.

Skills

Required

  • Bachelor's Degree in Computer Science or related technical field
  • 6+ years technical engineering experience
  • coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python
  • Ability to meet Microsoft, customer and/or government security screening requirements

Nice to have

  • Experience building production LLM-powered applications
  • RAG pipelines
  • prompt engineering
  • agent frameworks (Semantic Kernel, LangChain)
  • fine-tuning
  • strong judgment on evaluation, latency, and cost trade-offs at scale
  • AI-native development worki

What the JD emphasized

  • set the technical direction
  • architect core components
  • own complex systems end to end
  • define the bar for how agents are built, evaluated, and operated
  • mentor senior and staff engineers
  • drive technical strategies and engineering standards
  • own the architecture and lead the design, operation, and evolution of AI‑driven, end‑to‑end autonomous support workflows
  • foundational to Microsoft’s next‑generation Support experience
  • intersection of AI engineering, live‑site operations, compliance, and business transformation
  • production-ready, trustworthy, and scalable
  • complex, often ambiguous agentic support platform
  • run-state reliability
  • designated responsible individual (DRI)
  • customer trust, satisfaction, and sentiment
  • security, privacy, and Responsible AI architecture
  • assuring visible compliance evidence
  • observability, monitoring, and intervention architecture
  • multiple AI agents operating concurrently at scale
  • cross-team alignment
  • scalable engineering standards
  • negotiating and resolving conflicts
  • driving agreements
  • enables citizen developers to safely build AI agents
  • raising the engineering bar
  • mentoring senior and staff engineers
  • building and evaluating production agentic systems
  • Influencing technical strategy and roadmaps across organizational boundaries
  • building alignment among partner teams and senior leaders
  • shared architectural vision
  • automation across production and deployment
  • zero-touch deployment
  • safe change-deployment best practices
  • experimentation using feature flags/flighting
  • define the success and guardrail metrics
  • anticipate, determine, and confirm customer/user requirements and their feasibility
  • advocating for the security and privacy needs

Other signals

  • agentic support platform
  • AI-driven, end-to-end autonomous support workflows
  • production-ready, trustworthy, and scalable AI-managed support systems