AI Inference Systems & Optimization
Core
Build and maintain infrastructure for running Microsoft's frontier AI models, optimizing inference performance for reinforcement learning, synthetic data generation, and evaluation.
Role type
Senior IC machine-learning infrastructure engineer (inference systems)
Builds
Inference systems, distributed systems, profiling tools, and debugging utilities for large-scale AI workloads
Domain
Generative AI, distributed systems, high-performance computing
Deliverable
production ML models
Required skills
Generative AI architecture, open-source inference frameworks (vLLM, SGLang), Python, PyTorch, GPU kernel programming, Infiniband, NVLink, large-scale distributed systems
Preferred skills
AI/ML infrastructure, inference optimization, performance tuning
Responsibilities
Implement frontier AI research ideas, introduce new systems to improve inference performance, build tools for debugging bottlenecks and distributed issues, establish processes to enhance team productivity
Seniority
Senior, hands-on IC