About this role
Microsoft is hiring a Principal AI Optimization Software Engineer Lead on the AI Frameworks Group, based in Israel (multiple locations), working 3 days/week in-office with 50-75% travel. The AI Frameworks Group builds the software foundation that lets Microsoft deploy and run AI models efficiently across a rapidly evolving set of hardware platforms, aiming to make every relevant AI model run as efficiently as possible on every Microsoft AI accelerator.
This role focuses on pushing the limits of AI performance through ML algorithm innovation, advanced AI compilation and hardware optimization, runtime and serving optimizations, and innovations in distributed execution, working across the AI software stack and partnering with model, systems, compiler, and hardware teams. As a Principal-level individual contributor, responsibilities span technical leadership in code reviews and coding standards; leading system architecture and design decisions for complex, often ambiguous products; driving engineering excellence (tooling, automation, best practices); leading experimentation and rollout/deployment strategy; owning reliability and on-call (DRI) responsibilities including incident postmortems; and partnering with stakeholders to define and validate customer/user requirements.
Required qualifications: Bachelor's degree in Computer Science or related technical field, 8+ years of technical engineering experience coding in C++ and Python, and at least 2 years of experience designing and implementing AI kernels, AI optimization algorithms, or AI compilation techniques. Preferred: Master's degree in Computer Science or related field, and deep expertise in areas such as quantization, sparsity, speculative decoding, graph optimization, operator fusion, code generation, inference serving, batching and scheduling, or caching.
This position will be open for a minimum of 5 days, with applications accepted on an ongoing basis until filled.