Principal Software Engineer

Microsoft•Redmond, WA

12d•$142,800 - $304,200

About The Position

Help engineers deliver better software with less repetitive work through AI. As a Principal Software Engineer on the EPICS team that is part of the Agent 365 Foundations organization, you will build LLM-powered agents that translate engineering intent into tested, reviewable changes. You will remain hands-on in design, coding, and debugging while shaping technical direction across teams and making agentic workflows reliable, secure, and useful in day-to-day engineering. This individual-contributor role combines deep AI application engineering with practical judgment about what to automate and where people must remain in control. Success is measured by verified engineering outcomes—not simply by the volume of generated code. You will help define and track validated task completion, review usefulness, human intervention and rework, cycle time, defect rates, and cost per verified outcome. Microsoft’s mission is to empower every person and every organization on the planet to achieve more. As employees we come together with a growth mindset, innovate to empower others, and collaborate to realize our shared goals. Each day we build on our values of respect, integrity, and accountability to create a culture of inclusion where everyone can thrive at work and beyond.

Requirements

Bachelor's Degree in Computer Science or related technical field AND 6+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python OR equivalent experience.
Ability to meet Microsoft, customer and/or government security screening requirements are required for this role. These requirements include but are not limited to the following specialized security screenings: Microsoft Cloud Background Check: This position will be required to pass the Microsoft Cloud background check upon hire/transfer and every two years thereafter.

Nice To Haves

Master'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 OR Bachelor's Degree in Computer Science or related technical field AND 12+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python OR equivalent experience.
Hands-on experience building and delivering LLM-powered applications or agents that use tools and execute multi-step workflows, beyond personal use of AI coding assistants.
Solid software engineering fundamentals, including hands-on coding, debugging, and automated testing, with sound judgment about abstractions, interfaces, and maintainability.
Experience designing and operating distributed systems or cloud services, including state management, observability, security, reliability, and recovery from partial failures.
Ability to evaluate and improve agent behavior using task-level tests, traces, and failure analysis, and to distinguish plausible model output from correct, reproducible engineering results.
Demonstrated principal-level technical leadership across teams, including shaping architecture, aligning delivery, influencing decisions without direct authority, and mentoring engineers through hands-on work.
Experience with multi-agent coordination, durable workflow execution, or recovery from interrupted and partially completed agent tasks.
Depth in repository-aware context retrieval, code understanding, model routing, or fallback strategies, including trade-offs among quality, latency, reliability, and cost.
Experience building developer tools, repository services, build and test infrastructure, CI integrations, automated code review, or repair workflows used by engineering teams.
Experience with extensibility frameworks, plugin architectures, protocol design, declarative programming models, or manifest-driven extensibility.
Experience with Microsoft Copilot, Azure AI, or similar agentic platforms.
Experience scaling adoption of AI-powered engineering workflows and designing evaluations or experiments that connect agent use to measurable engineering outcomes.

Responsibilities

Build agents that carry authorized work from intent and design through implementation, test execution, code review, and remediation. Produce pull requests with attributable changes and evidence of what was checked, what passed, and what still needs review.
Design orchestration, tool interfaces, and context retrieval around real repositories, build and test systems, and CI pipelines. Use durable state and explicit ownership so interrupted work can resume and handoffs are recoverable.
Create LLM and agent evaluations and regression tests grounded in engineering tasks. Debug failures across models, prompts, context, and tools; use results to qualify changes and balance quality, reliability, latency, and cost.
Build secure, bounded execution with scoped permissions, explicit approval for privileged actions, and human review before changes are accepted. Make agent actions observable and attributable, with clear stop conditions when authorization or evidence is insufficient.
Deliver across teams from early validation to adoption. Align interfaces, dependencies, and ownership; learn from engineers using the workflows, compare against meaningful baselines, and connect usage to verified productivity and quality outcomes.
Set technical direction and turn ambiguous problems into achievable milestones. Write and review high-quality code and tests, simplify architecture, and mentor engineers through design, debugging, and delivery.