Kristof Gryzik
Team Lead at deepset
Cologne, North Rhine-Westphalia, Germany
Summary
🤩
Rockstar🎓
Top SchoolKristof Gryzik is a Team Lead based in Cologne with 8 years of software engineering experience, currently driving technical direction and delivery at deepset. He combines a strong mathematics background (MSc, RWTH Aachen) with hands-on expertise in Python, NLP, and MLOps to ship production-ready LLM applications and retrieval-augmented systems. As a significant contributor to the popular Haystack framework, he implemented secure private model support and integrations for deployment and cloud workflows. Kristof has progressed rapidly from engineer to technical lead, blending backend development, model orchestration, and DevOps to close the gap between research prototypes and scalable products. Colleagues describe him as pragmatic and detail-oriented, equally comfortable optimizing tokenization/loading pipelines as mentoring teams on production reliability. He also maintains an active open-source presence and a playful curiosity (project duck) that fuels practical experimentation.
8 years of coding experience
6 years of employment as a software developer
Master of Science - MS, Mathematics, 1,0, Master of Science - MS, Mathematics, 1,0 at RWTH Aachen University
Github Skills (23)
transformers10
python10
machine-learning10
large-language-models10
retrieval-augmented-generation10
api-design9
amazon-elasticsearch9
opensearch9
devops9
aws-elasticsearch9
elasticsearchquery9
api9
elasticsearch-api9
nlp9
elasticsearch9
Programming languages (7)
Github contributions (5)
deepset-ai/haystack
Nov 2021 - Sep 2022
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:
Back-end Developer & MLOps Engineer
Back-end Developer & MLOps EngineerContributions:50 reviews, 16 commits, 36 PRs in 9 months
Contributions summary:Kristof contributed significantly to enhancing the Haystack framework, particularly in supporting private models from Hugging Face through API tokens. They implemented features to enable secure access to models, modifying code related to tokenization and language model loading. The user also worked on integrating private models into retrievers and document store functionalities, showcasing a focus on production-ready LLM applications. Furthermore, the commits reflect expertise in deployment and Deepset Cloud integration, handling status codes and system configurations.
pythonbertfinetuningproduction-readyhuggingface-transformers
Senseering/se-mde-worker-examples
Jun 2020 - Jan 2025
Contributions:15 PRs, 14 pushes, 15 branches in 4 years 7 months
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.