Software Engineer II - Microsoft 365 Copilot inference infrastructure
Microsoft 365 Copilot is a groundbreaking productivity tool that leverages the power of large language models, user data, Microsoft Graph, and the web to drive unparalleled creativity and productivity.
Our team in Microsoft Search, Assistant, and Intelligence (MSAI) designs and operates the central infrastructure enabling Copilot experiences across Teams, Outlook, Word, PowerPoint, and more.
You’ll work on systems that scale to millions of users and deliver AI-driven capabilities that redefine how people work every day.
Our team is driving one of Microsoft’s most transformative technology efforts: bringing AI to every customer through the Microsoft 365 suite.
We combine deep technical innovation with product-facing impact, operating at massive scale.
We are proud of our collaborative culture and our track record of delivering results at scale.
Responsibilities
- Design, implement, and optimize core services that make Copilot fast, reliable, and intelligent.
- Work on complex problems in GPU capacity management, LLM inference, and AI efficiency at scale.
- Collaborate with engineers across Microsoft to build distributed systems, improve inference performance, and ensure resiliency for millions of users.
- Work with stakeholders to determine user requirements for a set of features.
- Contribute to design documents and identify dependencies for product areas with minimal oversight.
- Implement and maintain code for services and features, reusing components where applicable.
- Break down larger work items into smaller tasks and provide accurate estimates.
- Act as a Designated Responsible Individual (DRI) during on-call rotations to monitor and restore services for simple issues.
- Stay current with emerging technologies and patterns to improve reliability, efficiency, and performance at scale.
Qualifications
Required Qualifications
- Bachelor’s Degree in Computer Science or related technical field AND 2+ years of technical engineering experience coding in languages such as C, C++, C#, Java, JavaScript, or Python
- OR equivalent experience
- 2+ years of experience building distributed, near real-time, high-load systems
- 2+ years of experience translating requirements into feature implementations
Other Requirements
- Ability to meet Microsoft, customer and/or government security screening requirements, including the Microsoft Cloud Background Check (required upon hire/transfer and every two years thereafter).
Preferred Qualifications
- Bachelor’s Degree in Computer Science OR related technical field AND 4+ years of technical engineering experience
- OR Master’s Degree in Computer Science or related technical field AND 2+ years of technical engineering experience
- Familiarity with modern software design patterns (microservices, containers, caching, queuing).
- Experience with CUDA kernels, CPU/GPU performance optimization, network latency, and managing large-scale capacity fleets.
Microsoft is an equal opportunity employer and considers applicants without regard to age, ancestry, citizenship, color, family or medical care leave, gender identity or expression, genetic information, immigration status, marital status, medical condition, national origin, disability, political affiliation, protected veteran or military status, race, ethnicity, religion, sex, sexual orientation, or any other characteristic protected by law.
If you need assistance or accommodations due to disability during the application process, read more about requesting accommodations.
Seniority level
Not Applicable
Employment type
Full-time
Job function
Engineering and Information Technology
Industries
Software Development
#J-18808-Ljbffr