Sorry %%REM_ADDRESS%%, your request cannot be processed.For security reasons, it was blocked and logged.%%NINJA_LOGO%%If you believe this was an error please contact thewebmaster and enclose the following incident ID:[ #%%NUM_INCIDENT%% ]

Data Scientist

Resume posted by palatinuse in IT.

Desired position type: Any
Location: Saarbrücken Saarland, Germany

Contact palatinuse


Endre Palatinus is a Co-Founder and Data Scientist at d:AI:mond GmbH. He enjoys solving data science problems in R and Apache Spark, in particular, scientific​ data analysis and optimizing the performance of big data systems.


PhD in Computer Science (Big Data Analytics), Saarland University, 2011 – 2016

MSc in Computer Science (Software Engineering), University of Szeged, 2009 – 2011

BSc in Computer Science, University of Szeged, 2006 – 2009


Co-founder & Data Scientist, d:AI:mond GmbH, 2008-present:
Served as co-CEO. Responsible for B2B sales and finances. Worked as a data scientist.

Project: Data Integration in the Chemical Industry

I have completed a large-scale data integration and data mining project for a German chemical giant. I have written software for extracting ingredient lists and measurement results from wildly different Excel Vles with no Vxed schema. This involved using data mining and knowledge extraction techniques, as well as setting up ETL pipelines. I have closed the deal and was responsible for all parts of the project, including requirements specification, budgeting, and implementation.

Project: Quality Assurance and Performance Tuning of a Time-Series Library

I have completed a project for a German premium car manufacturer, where I have tested and tuned their big data system for storing and analyzing sensor data of prototype vehicles. This involved writing unit tests in Scala for a distributed system based on Apache Spark. In the performance tuning phase of the project, I have applied my research expertise in the big data analytics area and achieved a factor 5 performance boost. The system is used for crunching petabyte-scale datasets, and thus it required large-scale automatic VM orchestration and system setup. This project involved diving into the CAN bus architecture for sensor fusion, and system validating using signal temporal logic (STL) as well.

Project: Building a recommendation engine for wines

Implemented a hybrid item- and content-based recommendation engine using collaborative-filtering for wines. Deployed into production on Amazon’s private recommendation engine.

Project: Dynamic Pricing in the Hospitality Industry

Implemented data-pipelines from various booking, pricing and payment providers. Created dashboards for data-driven decision making. Implemented a model for dynamic pricing.


  • R
  • Shiny
  • Spark
  • Scala
  • SQL
  • Java
  • C/C++
  • Docker


    Database Technology, Research

Spoken Languages

    English (C1), German (fluent), Hungarian (native)