Senior Software Engineer- AI Frameworks

Microsoft’s AI Frameworks team develops software and engineering tools that enable AI models to run reliably and efficiently at cloud scale. The Senior Software Engineer owns and delivers components and projects across AI performance, benchmarking, automation, and developer tooling, improving model workloads and production platform capabilities.

Responsibilities:

• Design, implement, test, and operate production-quality components across AI frameworks, runtimes, benchmarking systems, performance tooling, and service integrations
• Benchmark, profile, debug, and optimize large language model training and inference workloads across GPUs and Microsoft hardware
• Build automation and observability that detect regressions, improve reproducibility, surface actionable insights, and accelerate model and hardware onboarding
• Drive scoped projects from problem definition through deployment, balancing delivery speed, maintainability, reliability, and measurable customer or capacity impact
• Partner with researchers, model teams, infrastructure owners, and hardware vendors to diagnose cross-stack issues and deliver production-ready solutions
• Contribute to technical design reviews, engineering standards, operational health, and mentoring of other engineers
• Embody Microsoft’s culture and values

Requirements:

• Bachelor's Degree in Computer Science or a related technical field and 4+ years of technical engineering experience coding in languages such as C++, or Python, or equivalent experience
• Ability to meet Microsoft, customer and/or government security screening requirements are required for this role
• Expertise in GPU or equivalent accelerator programming and kernel optimization using CUDA, Triton, or comparable technologies
• Experience using profiling and benchmarking to deliver measurable performance improvements, with an understanding of memory hierarchy, parallel execution, synchronization, and hardware utilization
• Familiarity with vLLM, SGLang, or equivalent inference frameworks, including their model execution, scheduling, batching, and KV-cache mechanisms
• Demonstrated technical ownership and cross-team collaboration, including independently delivering complex engineering changes into production
• Ability to use AI-assisted development tools effectively while maintaining sound engineering judgment and accountability for correctness, performance, and maintainability