Senior/Principal Software Engineer (AI Performance)

Quick Facts

• Role: Senior/Principal Software Engineer (AI Performance)
• Focus: End-to-end inference performance for OpenAI and other LLMs

Description

You will work across the AI software stack to benchmark, debug, and optimize LLM inference performance on NVIDIA/AMD GPUs and Microsoft hardware. The role involves building performance tooling to identify bottlenecks from model to systems and silicon, and enabling fast, scalable deployments with minimal hardware footprint.

Responsibilities

• Drive improvements to end-to-end LLM inference performance
• Measure and benchmark performance on NVIDIA/AMD GPUs and Microsoft silicon
• Optimize and monitor LLM performance; build software tooling for performance insights
• Enable fast time to market by building tools for porting models to new GPUs
• Design, implement, and test components for AI/DNN/LLM frameworks and tools
• Reduce complexity and improve efficiency of key pipelines
• Collaborate with internal and external partners

Requirements

• Bachelor’s degree in Computer Science or related technical field AND 4+ years technical engineering experience with coding in C/C++/C#/Java/JavaScript/Python (or equivalent)
• Ability to meet Microsoft, customer, and/or government security screening requirements, including Microsoft Cloud background check upon hire/transfer and every two years

Benefits

• Opportunity to work on fundamental abstractions, programming models, compilers, runtimes, libraries, and APIs for large-scale training/inference
• Hands-on role focused on end-to-end AI stack performance challenges