My research investigates emerging and fundamental problems in the field of language technology, combining linguistic insights with reproducible methods to address the challenges posed by textual, spoken and multimodal data.

Recent projects include designing pipelines for the construction of complex multilingual corpora, improving automatic speech recognition for verbatim transcription, and fine-tuning multimodal transformers for audiovisual content analysis.

Currently leading and defining both long-term and short-term strategy for my startup, conducting stakeholder interviews while evaluating MVPs and go-to-market strategies in collaboration with my co-founders. Open to collaborations! 🔍