Researcher - Efficient Architecture for LLMs
Core
Propose and develop novel research ideas to advance the state of the art in large language models (LLMs), focusing on efficient architectures, long-context enabling, data curation, and post-training methods.
Role type
Researcher - Efficient Architecture for LLMs
Builds
Novel research ideas and applied research projects for Huawei's LLM products and services
Domain
Artificial Intelligence / Large Language Models (LLMs)
Deliverable
research
Required skills
NLP fundamentals, LLM architecture design, transformer models, linear-attention models, Python, PyTorch, LLM training/inference stacks, experimental design, academic publishing
Preferred skills
Supervising researchers, tracking AI ecosystem advances
Technologies
PyTorch, Hugging Face Transformers, Megatron-LM, vLLM, Llama, Qwen, Mamba, GLA