Martin Mauch - Data Architect & Scientist

Mintraching, Germany

Experience

Jul 2023 - Dec 2023

6 months

Evaluation and scoring of various technologies as future telematics platform Kafka Streams, Spark, Splunk, Snowflake
Improve test framework and scalability of Telematics streaming service Scala, Property-Based Testing, Kafka, Kafka Streams, Kubernetes

Apr 2021 - Jun 2023

2 years 3 months

Magdeburg, Germany

Implementation of a Big Data Record Linkage Pipeline Cloudera Public Cloud, Spark, Hadoop, Hive, Kafka, Splink
Implementation of a CI/CD pipeline for the developed Big Data applications Ansible, Gitlab CI, Docker, Kubernetes
Creation of a PoC for automatic validation and correction of data, as well as record linkage Spark, Drools, Splink, Apache NiFi, Scala, Python
Set up of a new Big Data cluster for a European capital Cloudera Private Cloud, Ansible, Kerberos
Migration of Big Data applications to the new cluster Docker, Spark, Hive, Python

Aug 2020 - Dec 2023

3 years 5 months

Berlin, Germany

Design of the architecture and implementation of a prototype for the use of Industry 4.0 processes for individualized cancer therapy Petri Nets, Industry 4.0, Digital Twins, Scala

Apr 2018 - Oct 2020

2 years 7 months

Munich, Germany

Design and implementation of an algorithm to optimize the planning of production sequences subject to constraints Scala, Constraint Programming, Constraint Based Local Search, SAP
Research, design and development of a platform for processing telematics data Spark, Hadoop, Azure, Kafka
Analysis and improvement of telematics data quality Python, Pandas, scikit-learn, Spark, Time Series Analysis, Active Learning
Design and establishment of a data science workflow R, RStudio, Jupyter, DVC
Research, design and development of a central API Gateway which hides the complex system landscape of WN behind a simple interface Scala, GraphQL, REST
Conception and assistance in the establishment of agile processes in the IT department Scrum, Kanban, Pair Programming, Retrospectives, Root-Cause Analysis, Hypothesis-Driven Development

Nov 2008 - Apr 2018

9 years 6 months

Passau, Germany

Implementation of an algorithm for automatically generating, evaluating and selecting ad copies Ruby, Branch and Bound
Design and implementation of a method for creating statistical estimations of conversion rates R, RStudio, Knime, Rapidminer, Regression Trees, Bayesianmodels, Support Vector Regression
Implementation of an algorithm for creating statistical models of search engine auctions and maximizing profit given additional constraints Scala, Bayesian linear regression, spline models, Computational Algebra, quasi-Newton optimization
Prototyping of various algorithms. Coordination between data science and engineering teams MinHash, Bayesian Vector Auto-Regression, ARIMA, Jupyter, RStudio, Spark
Creation of an ontology for products, brands and relevant search terms Natural Language Processing, Neo4j
Design and implementation of an algorithm for optimal matching of products to search queries Scala, Branch and Bound, Graph DB, ontologies
Implementation of a data processing pipeline Scala, Spark
Conception, submission and execution of a government-funded research cooperation project (ZIM Koop) with the University of Kassel Java, Exponential Smoothing, Bayesian Models, Support Vector Machines, Graph DB, Ontologies
Conception and establishment of agile processes in the entire company Scrum, Kanban, Pair Programming, Retrospectives, Root-Cause Analysis, Hypothesis-Driven Development