Work on research projects such as “Validation and improvement of context grounding metric”, “Knowledge Distillation for Efficient LLM Systems”, automatic prompt optimization, GraphRAG summarization, and evaluation of AI-generated summaries
Analyze current metrics and propose improvements; implement upgraded Python implementations
Conduct literature reviews, build experimental setups, and implement prototypes in Iris.ai’s codebase
Benchmark and evaluate models and summarization methods; produce comparative analyses and evaluation reports
Design, implement, and test frameworks for knowledge distillation and prompt optimization in RAG and Agentic AI systems
Produce deliverables including Python implementations, prototypes, benchmarking results, and detailed reports
Full-time commitment for 3-6 months, 40 hours per week; remote collaboration with Research Team
Opportunity to carry out a Master Thesis project within the internship
Requirements
Being a Bachelor/Master student in а computer science major
Seeking a career with Machine Learning/NLP
Interest in and having some knowledge of NLP
Some experience in Python development is mandatory
Some knowledge and experience in Machine Learning
Interest in Iris.ai’s research projects and domain
Ability to work full-time for the period of the internship
Located within the European Timezone (+/-2 hours of CET)