Skills
LLM inference performance
Systems performance engineering
Distributed systems
About the Role
Join Microsoft’s Artificial Intelligence Performance team, where we build AI software that helps run advanced models across a wide range of environments—from high-end supercomputers to servers, devices, and browsers. This role focuses on inference performance for OpenAI and other leading LLMs, supporting some of the largest-scale workloads across Microsoft products.
Responsibilities
- Own and improve inference performance for state-of-the-art LLM models
- Work closely with hardware teams and internal/external partners to optimize end-to-end systems
- Collaborate directly with OpenAI on models hosted via Azure OpenAI service
- Analyze performance bottlenecks and drive engineering improvements that scale to very high throughput
- Contribute to a collaborative, inclusive engineering culture while partnering across teams
Requirements
- Experience building and optimizing production software systems
- Strong performance engineering fundamentals (profiling, benchmarking, latency/throughput tradeoffs)
- Experience working with AI/ML inference workloads or large-scale distributed systems
- Proficiency in at least one modern programming language used in backend services
Benefits
- Opportunity to work on AI infrastructure powering major Microsoft products
- Collaborate with experts across AI algorithms, systems, and purpose-built hardware
- Inclusive culture and team-oriented environment
This job was curated and enriched by FindJobHere to help your search. Apply on the original website: apply.careers.microsoft.com.
Learn how it works.