Responsibilities
Explore, co-design and optimize parallelisms, compute efficiency, distributed training/inference paradigms and algorithms to improve the scalability, efficiency, and reliability of GenAI and recommendation systems
• Innovate and co-design novel model deployment techniques for sustained scaling and hardware efficiency during GenAI and recommendation model serving
• Explore, prototype and productionize highly optimized ML kernels to maximize the utilization and performance of current and future accelerators for Meta's AI workloads
• Benchmark, analyze, model, and project the performance of AI workloads against a wide range of what-if scenarios and provide early input to the design of future hardware, models, and runtime, giving crucial feedback to the architecture, compiler, kernel, modeling, and runtime teams
• Guide Meta's AI HW requirements and design focusing on performance at System and Silicon levels. Co-design and optimize our AI HW and related software stack for Meta's future workloads, with technology pathfinding and evaluation of cutting-edge AI systems
• Lead cross-functional initiatives spanning multiple engineering organizations to drive high-impact technical milestones
Minimum Qualifications
• Currently has, or is in the process of obtaining a Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience. Degree must be completed prior to joining Meta
• A PhD in Computer Science, Electrical Engineering, Applied Mathematics, or a related technical field. (Completed or near completion.)
• Proven research experience in one or more of the following areas: computer architecture, operating systems, ML systems and kernels, ML compilers, model-system co-design, performance modeling of AI systems, prevailing accelerators/silicon architectures, ML training algorithms
• Hands-on proficiency with end-to-end AI hardware architecture or on-device mapping algorithm development, encompassing logic, architecture, and optimizations for performance, power, and area (Power, Performance, and Area) (PPA)
• Theoretical background and practical experience with AI models (e.g., Transformers, LLMs, Diffusion models, CNNs, Recommendation Models)
• Experience in system-level performance analysis, profiling, and benchmarking of AI workloads
• Experience in Python, including developing production-quality code or research prototypes and experience with at least one major AI framework
• Track record of publishing research papers at peer-reviewed conferences or journals, and experience in communicating technical results to cross-functional stakeholders
Preferred Qualifications
• Experience or knowledge of distributed machine learning systems and algorithm development
• Experience or knowledge of GenAI models, such as LLMs/LDMs or ranking and recommendation models, such as DLRM or equivalent
• Experience or knowledge of training/inference of large-scale deep learning models
• Familiarity with low-level programming for specialized hardware (e.g., CUDA, HIP, Triton) or hardware description languages (HDL)
• Experience with deploying AI agents and prevailing techniques for increased efficiency
• roven track record of achieving significant results as demonstrated by grants, fellowships, patents, as well as first-authored publications at leading workshops or conferences
• Experience working and communicating cross-functionally in a team environment
