About
Determined tech enthusiast with a love for efficiency, eager to solve complicated business problems in a complex environment. Interested in Start-Ups and people with a vision. Passionate about discussing bold ideas, their impact, and strategies for implementing them.
PhD, AI Specialist, Computer Scientist
I have a PhD in Artificial Intelligence (AI), in which I taught the computer to return better answers to complex questions using my strong background in Computational Logic, Computer Vision and Machine Learning. I have entrepreneurial experience with an own Start-up and look forward to founding my next one. In my free time I'm a black belt and martial arts teacher.
If you think we should talk, please contact me.
Resume
Ambitious computer scientist with strong background in Machine Learning and Computational Logic and a passion for efficient and scalable systems.
Professional Experience
Platform Architect, Knowledge Graph Engineer
2022 - present
COSMO CONSULT GmbH, Dresden, Germany
Design and development of an enterprise knowledge graph system to model the whole business domain of COSMO Consult and integrate the existing systems landscape.Technical Director
2021 - 2022
akili:innovation GmbH, Dresden, Germany
Leading the development of software for Card- and Accessmanagement at airports, stealmills and universities.Co-Founder, Technical Director
2012 - 2015
FingerCoding UG, Dresden, Germany
Lead the development of interactive E-books for children together with the Swiss book publisher Diogenes in a team of 4 developers.Education
Ph.D. Knowledge Representation & Reasoning
2017 - 2020
Technical University of Dresden, Dresden, Germany
Improved methods for query answering over temporal data resulting in multiple publications.
Research Visit
2014 - 2015
Weizmann Institute of Science, Rehovot, Israel
Development of an enhanced algorithm for 3D reconstruction of objects from images.
Diploma (M.Sc.) Computer Science
2011 - 2017
Technical University of Dresden, Dresden, Germany
Specialized in Computational Logic, Artificial Intelligence and Machine Learning.
Publications
Computational Logic & Knowledge Representation
Automatic Translation of Clinical Trial Eligibility Criteria into Formal Queries
In Proc. of the 9th Workshop on Ontologies and Data in Life Sciencs (ODLS’19), part of The Joint Ontology Workshops (JOWO’19). Ed. by M. Boeker, L. Jansen, F. Loebe, and S. Schulz. CEUR Workshop Proceedings. 2019. https://lat.inf.tu-dresden.de/research/papers/2019/XFB-ODLS15.pdfClosed-World Semantics for Conjunctive Queries with Negation over \(\mathcal{ELH}_\bot\) Ontologies
In Proc. of the 28th International Joint Conference on Artificial Intelligence (IJCAI'19). AAAI Press, 2019, pp. 6131-6135. https://dx.doi.org/10.24963/ijcai.2019/849Closed-World Semantics for Conjunctive Queries with Negation over \(\mathcal{ELH}_\bot\) Ontologies
In Proc. of the 16th European Conf. on Logics in Artificial Intelligence (JELIA’19). Ed. by F. Calimeri, N. Leone, and M. Manna. Vol. 11468. Lecture Notes in Artificial Intelligence. Rende, Italy: Springer, 2019, pp. 371– 386.https://dx.doi.org/10.1007/978-3-030-19570-0_24
Finding New Diamonds: Temporal Minimal-World Query Answering over Sparse ABoxes
In Proc. of Rules and Reasoning (RuleML+RR'19). Ed. by Fodor P., Montali M., Calvanese D., Roman D. Lecture Notes in Computer Science, vol 11784. Springer, Cham.https://dx.doi.org/10.1007/978-3-030-31095-0_1
Patient Selection for Clinical Trials Using Temporalized Ontology-Mediated Query Answering
In Companion Proceedings of the The Web Conference 2018, pp. 1069-1074. 2018. https://dx.doi.org/10.1145/3184558.3191538Fuzzing and verifying RAT refutations with deletion information
In the Thirtieth International Flairs Conference. 2017. https://aaai.org/ocs/index.php/FLAIRS/FLAIRS17/paper/view/15492Machine Learning & Computer Vision
Solving uncalibrated photometric stereo using fewer images by jointly optimizing low-rank matrix completion and integrability
Journal of Mathematical Imaging and Vision, 60 no.4, 2018, pp. 563-575.https://doi.org/10.1007/s10851-017-0772-y
Efficient likelihood learning of a generic CNN-CRF model for semantic segmentation
In ArXiv abs/1511.05067, 2015.https://arxiv.org/abs/1511.05067v2