2 days ago
Vancouver, CanadaStaff+
Base Salary
$188k - $304k/yr
Responsibilities
- Lead technical strategy for enabling and optimizing frontier-scale AI models across Microsoft AI accelerators and cloud-scale AI infrastructure.
- Architect and optimize AI systems across hardware, compilers, kernels, frameworks, runtimes, and distributed infrastructure.
- Partner with hardware architecture teams on hardware-software co-design, accelerator features, memory systems, interconnects, execution models, and silicon roadmaps.
- Optimize kernels, communication, memory movement, quantization, attention, mixture-of-experts, and other AI workloads.
- Architect distributed training and inference solutions spanning large accelerator clusters.
- Drive model enablement and performance improvements across PyTorch, Triton, vLLM, SGLang, and related AI ecosystems.
- Lead architecture reviews and cross-organization technical initiatives, mentor engineers, and provide recommendations for long-term AI infrastructure strategy.
Requirements
- Bachelor's degree in Computer Science or a related technical field and 6+ years of technical engineering experience with coding, or equivalent experience.
- Experience partnering with hardware architecture teams on hardware-software co-design, accelerator enablement, or performance optimization.
- Ability to meet Microsoft, customer, and/or government security screening requirements, including Microsoft Cloud Background Check requirements.
- Preferred experience includes 7+ years developing and optimizing high-performance AI systems, kernels, or accelerator software using CUDA, ROCm, Triton, or similar programming models.
- Preferred qualifications include experience with large-scale AI workloads, attention, mixture-of-experts, quantization, FP8, KV-cache management, memory efficiency, and foundation models.
- Preferred qualifications include experience designing distributed training or inference systems using tensor, pipeline, expert, or sequence parallelism.
- Preferred qualifications include deep knowledge of PyTorch and production-scale training or inference optimization.
- Preferred qualifications include leading complex initiatives across multiple engineering organizations and recognized contributions through publications, patents, or open-source work.
Benefits
- Flexible hybrid work model with three days per week in the office.
- Certain roles may be eligible for benefits and other compensation.
Tech Stack
Categories
About Microsoft
Microsoft develops operating systems, productivity software, cloud services, developer tools, and consumer devices for individuals, enterprises, and governments. Its main products include Windows, Microsoft 365, Azure, Visual Studio/GitHub, Xbox, and LinkedIn; revenue comes from software subscriptions and licenses, cloud consumption, hardware sales, and advertising. Founded in 1975 and headquartered in Redmond, Washington, Microsoft is a public company traded on Nasdaq.