LLM Evaluation, Guardrailing & EU AI Act Compliance — Applied AI/NLP Advisory

I work at the intersection of LLM evaluation, trustworthy AI, and multilingual NLP, with ~13 years of applied experience across industry, applied research, and regulated finance.

Areas I go deep on:

• LLM evaluation, red-teaming, and guardrailing

• RAG groundedness, contradiction and cross-lingual consistency checking

• Multilingual NLP and information retrieval

• EU AI Act operationalisation and LLM governance

• Prompt management and PromptOps

Background: PhD in Computer Science (University of Bonn); applied research at Fraunhofer IAIS; LLM evaluation, red-teaming and AI Act work in regulated finance. Working languages: EN/DE/ES/FR/NL.