Principal Software Engineer

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

The Principal Software Engineer will architect and evolve the core runtime infrastructure for a scalable platform to develop and run copilot workloads, enabling intelligent agents in Microsoft 365. This involves designing and implementing orchestration patterns for agent collaboration, supporting long-running tasks, extensibility, and multi-agent collaboration.

What you'd actually do

  1. Architect and evolve the core runtime infrastructure to support.
  2. Design and implement scalable orchestration patterns for agent collaboration, including delegation, sub-agent invocation, and shared memory contexts.
  3. Partner with cross-functional teams to ensure runtime stability, performance, and security.
  4. Drive innovation in agentic patterns such as proactive agents, long running tasks, async workflows, and dynamic skill selection.
  5. Contribute to the platform roadmap and influence long-term technical strategy.

Skills

Required

  • Bachelor's Degree in Computer Science or related technical field AND 8+ years technical engineering experience with 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

  • 10+ years of experience in software engineering with a focus on distributed systems, runtime architecture, or platform engineering.
  • Proven track record of technical leadership at scale, ideally in runtime or orchestration systems.
  • Deep understanding of extensibility frameworks, plugin architectures, and protocol design.
  • Solid coding skills in C#, C++, or equivalent systems-level languages.
  • Experience with LLM-based systems, agentic workflows, or AI orchestration is a plus.
  • Experience working on Microsoft Copilot, Azure AI, or similar agentic platforms.
  • Familiarity with declarative programming models and manifest-driven extensibility.
  • Demonstrated ability to lead cross-org initiatives and influence without authority.

What the JD emphasized

  • extensible runtime infrastructure
  • LLM-powered agents
  • agent-based computing
  • long running tasks
  • multi-agent collaboration
  • runtime stability
  • performance
  • security
  • proactive agents
  • async workflows
  • dynamic skill selection

Other signals

  • building AI workflows for productivity
  • intelligent agents into the daily workflow
  • extensible runtime infrastructure
  • LLM-powered agents
  • agent-based computing
  • long running tasks
  • multi-agent collaboration