Sr. Staff, ML Researcher - LLM Algorithmic Optimization
Core
Inventing, designing, and implementing efficient algorithms to optimize large language model inference on custom DNN accelerators.
Role type
Sr. Staff ML Researcher (LLM Algorithmic Optimization)
Builds
Optimized inference algorithms for proprietary DNN accelerators
Domain
Generative AI, Large Language Models, Hardware-Accelerated Computing
Deliverable
production ML models
Required skills
Advanced mathematics, Python programming, OOP design, Transformer architecture knowledge, Algorithm design, Numerical techniques, DNN accelerator optimization
Preferred skills
Experience with transformer architecture
Technologies
Python, DNN accelerators, Transformer models
Responsibilities
Design efficient algorithms for LLM inference, Implement algorithmic solutions on DNN hardware, Collaborate with mathematicians and ML engineers on advanced research
Seniority
Sr. Staff, hands-on IC
