Intern Researcher - Efficient Architecture for LLMs
Core
Researching efficient architectures and scalability for large language models (LLMs), focusing on long-context capabilities, data curation, and post-training methods.
Role type
Research Intern (PhD/Masters level)
Builds
Novel research ideas, experiments, and findings for LLM efficiency and scalability.
Domain
Artificial Intelligence / Large Language Models / NLP
Deliverable
research
Required skills
NLP fundamentals, LLM architectures (Transformers, Linear-attention models like GDN/Mamba/GLA), Python, PyTorch, experimental design, data analysis
Preferred skills
Diffusion models
Responsibilities
Propose and explore novel research ideas, execute experiments and analyze results, publish in top-tier ML/NLP conferences, track ecosystem advances
Seniority
Intern (Graduate student)