Research Scientist, Systems ML - SW/HW Co-Design - Inference

$117,000 - $173,000/Yr

Meta - Bellevue, WA

Full-time - Entry Level

Bellevue, WA

Web Search Portals, Libraries, Archives, and Other Information Services

About the position

Meta is seeking a Research Scientist to join our Research & Development teams, focusing on Systems Machine Learning (ML) with an emphasis on software/hardware co-design for inference. The ideal candidate will possess industry experience in AI Infrastructure and will be tasked with applying their skills to tackle some of the most critical and exciting challenges in the web domain. This position is available in multiple locations, reflecting Meta's commitment to innovation and excellence in technology. The Kernel team is dedicated to maximizing inference performance for Generative AI and Recommendation models by developing high-performance kernels. Our expertise lies in creating specialized kernels that significantly enhance the efficiency of these models. Notably, we have successfully developed and deployed the first FP8 kernel in Meta's production environment, along with FBGEMM TBE. By continuously advancing our kernel optimization capabilities, we aim to improve user experiences and drive innovation in Generative AI and Recommendation systems. The E2E Performance team focuses on optimizing the end-to-end performance of Generative AI and Recommendation models. We utilize various parallelism strategies and distributed inference techniques to enhance time-to-interaction (TTIT) and time-to-first-token (TTFT) for large language models (LLM) and latent diffusion models (LDM). Our relentless pursuit of performance improvements has led to significant achievements, such as enabling the use of AMD GPUs for GenAI production applications and optimizing their performance. Our ongoing efforts are geared towards the continuous enhancement of these models' performance, ultimately providing users with more responsive and seamless interactions with Generative AI.

Responsibilities

• Apply relevant AI infrastructure and hardware acceleration techniques to build and optimize intelligent ML systems that enhance Meta's products and experiences.
• Develop high-performance kernels and various parallelism techniques to improve end-to-end performance.
• Set goals related to project impact, AI system design, and infrastructure/developer efficiency.
• Directly or indirectly influence partners to deliver impact through comprehensive, data-driven analysis.
• Drive large-scale efforts across multiple teams to achieve project objectives.
• Define use cases and develop methodologies and benchmarks to evaluate different approaches.
• Utilize in-depth knowledge of how the ML infrastructure interacts with surrounding systems.

Requirements

• Currently has, or is in the process of obtaining a Bachelor's degree in Computer Science, Computer Engineering, or a 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, or a 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).
• Experience developing AI-System infrastructure or AI algorithms in C/C++ or Python.
• Must obtain work authorization in the country of employment at the time of hire, and maintain ongoing work authorization during employment.

Nice-to-haves

• Experience or knowledge of training/inference of large-scale AI models.
• Experience or knowledge of distributed systems or on-device algorithm development.
• Experience or knowledge of recommendation and ranking models.

Benefits

• Competitive salary ranging from $117,000 to $173,000 annually.
• Opportunities for professional development and career growth.
• Access to cutting-edge technology and resources.
• Collaborative and inclusive work environment.
• Flexible work arrangements and remote work options.