| Microsoft Careers

What you'll do

• Design and implement core inference infrastructure for serving advanced AI models in production.
• Identify and drive improvements to end-to-end performance and efficiency of state-of-the-art LLMs and GenAI models.
• Develop efficient load scheduling and balancing strategies for high-throughput, low-latency environments.
• Scale the platform to support growing inferencing demand while maintaining high availability.
• Deliver critical capabilities required to serve cutting-edge Gen AI models quickly.
• Collaborate with internal and external partners to drive new features and platform capabilities.

What we're looking for

• 2+ years of technical engineering experience in software development using C, C++, C#, Java, or Golang.
• Experience with high-scale, reliable online systems and real-time services requiring low latency and high throughput.
• Knowledge of network architecture, including HTTP, TCP protocols, authentication, and session management.
• Proficiency in OSS, Docker, Kubernetes, and experience with C++ or Golang.
• Ability to independently lead projects and collaborate effectively with internal and external partners.
• Strong foundation in software engineering principles, distributed computing, and system architecture.