Markus Paff
Senior Solutions Architect at beVisioneers: The Mercedes-Benz Fellowship
Dusseldorf, North Rhine-Westphalia, Germany
Summary
🤩
Rockstar🎓
Top SchoolMarkus Paff is a Senior Solutions Architect based in Düsseldorf with six years of experience blending product management, hands-on engineering and technical leadership across startups and enterprise vendors. He has built and led technical products from his co-founded social-intelligence SaaS to product roles at deepset and carbonfuture, and now shapes solutions at Elastic. Markus contributes to notable open-source AI tooling—maintaining documentation and touching retriever code in deepset-ai/haystack—bringing practical RAG and semantic search experience to production LLM applications. He mentors young innovators through the Mercedes‑Benz beVisioneers fellowship, pairing technical guidance with leadership coaching. Trained as a computer scientist at RWTH Aachen, he combines rigorous academic foundations with a maker’s mentality and a knack for turning research-grade ML ideas into usable products. Colleagues know him for bridging product strategy and developer ergonomics to accelerate adoption of complex AI systems.
6 years of coding experience
9 years of employment as a software developer
Mathematical-Technical Software Developer (MATSE), Apprenticeship, Mathematical-Technical Software Developer (MATSE), Apprenticeship at Industrie- und Handelskammer AachenBachelor of Science (B.Sc.), Scientific Programming, Bachelor of Science (B.Sc.), Scientific Programming at FH AachenMaster of Science (M.Sc.), Computer Science, Master of Science (M.Sc.), Computer Science at RWTH Aachen University
English, German
Github Skills (9)
python10
sphinx10
documentation10
large-language-models9
retrieval-augmented-generation9
nlp8
machine-learning8
generative-ai8
pytorch7
Programming languages (3)
Github contributions (5)
deepset-ai/haystack
Sep 2020 - Dec 2021
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:15 reviews, 31 commits, 61 PRs in 1 year 3 months
Contributions summary:Markus contributed significantly to the Haystack documentation, updating and maintaining various documentation versions. Their work included adding new documentation versions, updating directory structures, and incorporating the latest docstring and tutorial changes. The user also made code adjustments in specific files like `retriever/sparse.py` and `retriever/dense.py`, indicating some involvement with core functionality.
pythonbertfinetuningproduction-readyhuggingface-transformers
mpangrazzi/haystack-website
Oct 2020 - Mar 2022
Haystack landing page with documentation, use cases etc.
Contributions:273 commits in 1 year 5 months
caseshaystackuse-cases
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.