Intern Researcher – Efficient Architecture for LLMs

About the role

Assist in proposing and exploring novel research ideas to improve the efficiency and scalability of large language models. Participate in applied research projects focused on long‑context LLMs, covering efficient architectures, data curation, and post‑training methods. Collaborate on end‑to‑end projects by designing experiments, analyzing results, and presenting findings. Publish research in top‑tier ML and NLP conferences and track advances across the LLM ecosystem to provide actionable insights.

Key responsibilities

• Propose and explore novel research ideas for efficient LLM architectures.
• Conduct experiments on long‑context models, data curation, and post‑training techniques.
• Analyze experimental results and present findings to the team.
• Publish papers at leading machine‑learning and NLP conferences.

Required profile

• Currently pursuing a Ph.D. or Master’s in Computer Science, Software Engineering, or a related field.
• Deep understanding of NLP and large language model fundamentals with strong theoretical grounding in machine learning.
• Excellent oral and written communication skills.
• Ability to work collaboratively in a research‑oriented environment.

Required skills

• Strong programming skills in Python and expertise in PyTorch.
• Experience with modern LLM architectures, including transformer models (e.g., Llama, Qwen).
• Knowledge of linear‑attention models such as GDN, Mamba, and GLA.
• Experience training and evaluating large language models; familiarity with diffusion models is a plus.