This role pays more than
62%
of similar roles. Most pay
$174,600–$231,000
— the shaded band above.
At the midpoint, this role pays about
$209k
versus about
$203k
for comparable roles.
Based on 240 similar postings.
Employer
About Microsoft
Microsoft Corporation is a global technology leader producing software, hardware, and cloud services including Windows, Office 365, Azure cloud platform, Xbox gaming, and Surface devices. Industry: Software & Cloud Computing
Microsoft currently has
597 open roles
on FindRole.
Listed pay typically runs
$119,800–$234,700
across 570 roles with salary data.
As a Principal Software Engineer on the EPICS team within the Agent 365 Foundations organization, you will build LLM-powered agents designed to translate engineering intent into tested, reviewable code changes. You will be responsible for designing orchestration, tool interfaces, and context retrieval while building secure, bounded execution environments with scoped permissions. Your daily work involves developing agentic workflows, creating evaluation systems for model performance, and managing CI pipelines to ensure reliable automation. The role requires proficiency in languages such as C, C++, C#, Java, JavaScript, or Python, alongside expertise in distributed systems, durable state management, and repository-aware context retrieval. You will solve the technical challenge of making AI-driven engineering tasks reproducible and secure, balancing quality, latency, and cost while mentoring others through complex design, debugging, and delivery phases to improve overall developer productivity.
What does a Software Engineer earn?
Median $196000 from 2121 postings across 148 companies.
Build LLM-powered agents that translate engineering intent into tested, reviewable code changes.
Design orchestration, tool interfaces, and context retrieval systems for real repositories and CI pipelines.
Create and manage LLM evaluation suites and regression tests grounded in specific engineering tasks.
Implement secure, bounded execution environments with scoped permissions and human-in-the-loop approval gates.
Define technical direction by turning ambiguous problems into actionable milestones and simplified architectures.
Develop and maintain durable state management to ensure agentic workflows can recover from interruptions.
Measure and track verified engineering outcomes like cycle time, defect rates, and cost per outcome.
What we're looking for
Bachelor's Degree in Computer Science or related field and 6+ years of technical engineering experience in languages like C, C++, C#, Java, JavaScript, or Python.
Ability to pass Microsoft Cloud background checks.
Master's Degree in Computer Science and 8+ years of experience, or a Bachelor's Degree and 12+ years of experience (preferred).
Hands-on experience building and delivering LLM-powered applications or agents using tools and multi-step workflows (preferred).
Solid software engineering fundamentals including coding, debugging, automated testing, and judgment on abstractions and maintainability (preferred).
Experience designing and operating distributed systems or cloud services with focus on state management, observability, and security (preferred).
Ability to evaluate agent behavior using task-level tests and distinguish plausible model output from correct results (preferred).
Demonstrated principal-level technical leadership including architecture shaping, influencing decisions, and mentoring engineers (preferred).
Azure
Kubernetes
Infrastructure as Code
Python
C#
Java
C++
JavaScript
Distributed Systems
Microsoft 365
Telemetry
Automated Testing
AI Agents
Provisioning Workflows
Python
Large Language Models
Prompt Engineering
LangChain
SageMaker
Vert.x
DialogFlow
AWS
GCP
React
Angular
SwiftUI
Kotlin
Java
TypeScript
Spring
Express
NodeJS
Distributed Systems
Full-stack Development