AI Research Engineer (Master's Thesis)
Valamis Group Oy, Finland
- Built and evaluated a context-aware AI assistant for Valamis's LMS platform, using Retrieval-Augmented Generation (RAG) to ground an LLM in domain knowledge for automated reporting and business-intelligence queries over corporate learning and engagement data.
- Designed a hybrid retrieval pipeline (deterministic column mapping, intent detection, and dense semantic search over a 37-document knowledge base) with two LLM-as-judge evaluators validated against human ratings, raising answer quality to 82.7% (a +13.6-point gain over the manual baseline) and the hardest business-strategy questions from 34.7% to 76.7%; retrieval reached MRR 0.96 and Precision@1 0.93.
- Delivered the validated system to Valamis's development environment, working across AI, product, and platform teams to align outcomes with the product roadmap.