Research Scientist, Systems ML - SW/HW Co-Design - Inference
META - Menlo Park, California, United States, 94029Work at META
Overview
- Apply
Overview
Research Scientist, Systems ML - SW/HW Co-Design - Inference Responsibilities
Apply relevant AI infrastructure and hardware acceleration techniques to build & optimize our intelligent ML systems that improve Meta's products and experiencesDevelop high performance kernels and different parallelism techniques to improve E2E performance.Goal setting related to project impact, AI system design, and infrastructure/developer efficiencyDirectly or influencing partners to deliver impact through deep, thorough data-driven analysisDrive large efforts across multiple teamsDefine use cases, and develop methodology & benchmarks to evaluate different approachesApply in depth knowledge of how the ML infra interacts with the other systems around itMinimum 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.Currently has, or is in the process of obtaining, a PhD degree in Computer Science, Computer Vision, Generative AI, NLP, relevant technical field, or equivalent practical experience. Degree must be completed prior to joining Meta.Specialized experience in one or more of the following machine learning/deep learning domains: Model compression, hardware accelerators architecture, GPU architecture, machine learning compilers, or ML systems, AI infrastructure, high performance computing, performance optimizations, or Machine learning frameworks (e.g. PyTorch), numerics and SW/HW co-designExperience developing AI-System infrastructure or AI algorithms in C/C++ or PythonMust obtain work authorization in the country of employment at the time of hire, and maintain ongoing work authorization during employment.Preferred Qualifications
Experience or knowledge of training/inference of Large scale AI modelsExperience or knowledge of distributed systems or on-device algorithm developmentExperience or knowledge of recommendation and ranking models