Tunga Agricultural Chatbot
Published:
A Kinyarwanda telephone voicebot that answers farmers’ questions from verified agricultural knowledge. Now used in Rwanda’s Ministry of Agriculture call center.
Portfolio
This is an excerpt of my projects — a selection of work across industry, research, teaching, and the public sector.
Rwanda National GPU Data Center
Published:
Helped Rwanda with its first dedicated GPU server and conceptualize a national HPC center for sovereign public-sector AI.
German Municipal RAG Chatbot
Published:
Built a RAG chatbot that gives citizens conversational, sourced answers about German municipal services from official documentation.
Project-Based Learning: Chatbot Challenge
Published:
Designed and led project-based TU Berlin courses where students shipped working chatbots — from tourism bots and games to systems that train people against science denial.
AI Infrastructure & Efficient LLM Deployment
Published:
Shortly after ChatGPT’s release, the first open-source LLMs started appearing - and almost immediately ran into a practical problem: there was no standard, reliable way to actually deploy them. Every model came with its own quirks, hardware requirements, and setup process. I initiated an open-source project to build a deployment platform that made running these models a solved problem rather than a fresh engineering exercise every time.
Federated Chatbots Consultancy
Published:
Advised a major German IT company on federated multi-agent chatbot architecture and improved their modeling and evaluation pipeline.
Legal Semantic Search Platform
Published:
Implemented a semantic search platform that finds legal documents by meaning rather than exact keyword matches.
Retail Conversational Information System
Published:
Built a Rasa-based in-house chatbot so retail employees could ask questions and get answers from internal company knowledge.
dfki.de Website Relaunch
Published:
Tech-led the relaunch of DFKI’s institutional website — over 180,000 pages across 25 research departments — on time and on budget.
FREME Project
Published:
Led a 15-person international team transferring multilingual semantic NLP technologies to industry; rated excellent by the EU.