Research Scientist, Systems ML - SW/HW Co-Design - Inference
Description For Research Scientist, Systems ML - SW/HW Co-Design - Inference
Meta is seeking an experienced Research Scientist to join their Research & Development teams, specifically focusing on AI Infrastructure. The role is part of two crucial teams: the Kernel team and the E2E Performance team. The Kernel team specializes in maximizing inference performance for Generative AI and Recommendation models through high-performance kernel development, having achieved significant milestones like implementing the first FP8 kernel in Meta's production. The E2E Performance team focuses on optimizing end-to-end performance of Generative AI and Recommendation models using various parallelism strategies and distributed inference techniques.
The position offers an opportunity to work on cutting-edge AI infrastructure projects, developing high-performance kernels and optimization techniques that directly impact Meta's products and user experiences. The role requires deep expertise in machine learning systems, hardware acceleration, and performance optimization, with a focus on large-scale AI model deployment and optimization.
Successful candidates will join a team that has demonstrated significant achievements in AI infrastructure, including enabling AMD GPUs for GenAI production applications and optimizing their performance. The role offers competitive compensation, including a base salary range of $117,000 to $173,000, plus bonus, equity, and comprehensive benefits.
This position is ideal for candidates with a PhD in Computer Science or related fields, who have a strong background in machine learning systems, hardware accelerators, and high-performance computing. The role provides an opportunity to work on some of the most challenging and impactful problems in AI infrastructure, directly contributing to Meta's mission of connecting people and building the future of social technology.
Responsibilities For Research Scientist, Systems ML - SW/HW Co-Design - Inference
- Apply AI infrastructure and hardware acceleration techniques to build & optimize intelligent ML systems
- Develop high performance kernels and different parallelism techniques to improve E2E performance
- Goal setting related to project impact, AI system design, and infrastructure/developer efficiency
- Deliver impact through deep, thorough data-driven analysis
- Drive large efforts across multiple teams
- Define use cases, and develop methodology & benchmarks to evaluate different approaches
- Apply in depth knowledge of how the ML infra interacts with other systems
Requirements For Research Scientist, Systems ML - SW/HW Co-Design - Inference
- PhD degree in Computer Science, Computer Vision, Generative AI, NLP, or relevant technical field
- Specialized experience in machine learning/deep learning domains
- Experience developing AI-System infrastructure or AI algorithms in C/C++ or Python
- Must obtain work authorization in country of employment
Benefits For Research Scientist, Systems ML - SW/HW Co-Design - Inference
- Bonus
- Equity
- Benefits package
Jobs Related To Meta Research Scientist, Systems ML - SW/HW Co-Design - Inference
