WE NEED YOU
We are at the forefront of Open Large Language Models (LLMs), working closely with leading research communities to build open, auditable, and responsible AI technologies, with a strong focus on performance, transparency, and language diversity.
In Vietnam, we develop and contribute to truly open AI research and applied systems, aiming to strengthen Vietnamese language models and practical AI architectures that can be deployed in real-world environments.
As an AI Intern, you will work on cutting-edge open-source AI projects, combining model optimization, evaluation, and advanced retrieval-augmented generation (RAG) research
WHAT YOU WILL BUILD
1. Improving the performance of VinaSmol: a SmolLM with Vietnamese langage.
Evaluate and Benchmark the current VinaSmol model
Find Vietnamese dataset source to continue the model training
Create our specified training dataset with automation tools (N8N) from some current media source (YT, Vietnamese media sites, etc..)
Possibility to participate to benchmarking event organized by Minister of Science and Technology (MOST)
2. Improve and stabilize OpenRAG
Efficient detection of hallucinations in the context of RAG
Automatic evaluation of RAG systems
Explore other research modes: Graph RAG
Agentic Systems with multi-step workflows

REQUIREMENTS
Technical skills:
Python, good understanding of Machine Learning and NLP
Linux and Open Source development environments
Bonus: MLOps techniques
Soft skills:
Autonomy and initiative
Ability to work in a team and document ones work
Strong interest in applied research and innovation

WHY YOULL LOVE WORKING WITH US
Work in an international team with high skilled people
Gain hands-on experience with real product development and testing for a large-scale OpenSource project.
Opportunity to be an official member of LINAGORA after the internship period
Flexible and balanced work-life environment.
Participate in OpenSource communities and conferences in Vietnam
Modern working space, free coffee