Software Architect, Data Engineer, Search and Machine Learning Consultant
- Verfügbarkeit einsehen
- 4 Referenzen
- 80‐120€/Stunde
- 81375 München
- Umkreis (bis 200 km)
- bg | de | en
- 02.09.2019
Kurzvorstellung
PhD in Computer Science (Dr.-Ing.), Max Planck Institute, 2008
Auszug Referenzen (4)
"Die Kombination aus fachlichem und technischen Wissen von Herrn Dr. [...] hat eindeutig zum Projekterfolg beigetragen."
10/2018 – 6/2019
Tätigkeitsbeschreibung
Designed and implemented a web application for text analysis and classifi-cation of news articles relevant to the business case of the client. Used ex-tensively Elasticsearch, Scala, Apache Spark, scikit-learn, python, AngularJS.
Gathered, cleaned, prepared and evaluated training data for classification.
Continuously optimized the classification model using a feedback loop.
Spezialeffekte, Data Science, Big Data, Data Mining, Scikit-learn, Apache Spark, Python, Scala
"Ohne die vorausschauende Arbeitsweise von Herrn Dr. [...] hätten wir die AWS Cloud Anwendung nicht in time und budget erstellen können."
9/2017 – 3/2019
Tätigkeitsbeschreibung
Designed the overall cloud architecture of a solution for semantic advertisement targeting based on AWS, Elasticsearch and docker.
Designed and implemented a semantic matching algorithm for advertise-ment targeting based on Natural Language Processing and deep learning.
Designed and implemented a low-latency scalable web service to deliver the results of the matching algorithm based on Ratpack and RxJava and running on several EC2 nodes in AWS.
Designed the index structure and optimized Elasticsearch queries to enable fast communication between the distributed components.
Configured and maintained the Elasticsearch cluster to ensure high availa-bility and scalability.
Configured Filebeat and Elasticsearch to monitor the application logs and performance.
Data Science, Big Data, Business Intelligence (BI), Data Mining, Datenanalyse, Administration von Datenbanken, ETL, Continuous Delivery, Configuration Management, Continuous Integration, Keras, Logistische Regression, Maschinelles Lernen, Scikit-learn, Apache Spark, Mustererkennung, Named-entity recognition (NER), Natural Language Processing, Spracherkennung, Text Mining, Text-Extraction, Textklassifikation, Debian Linux, Linux (Kernel), Ubuntu, Scrum, Apache, Apache HTTP Server, Jetty, Nginx, Enterprise Architect (EA), Objektorientierte Analyse (OOA), Objektorientierte Design (OOD), Objektorientierte Software-Entwicklung, Software Architecture, Software Design, Apache Maven, Application Development, Backend, Bash Shell, Reactive Programming, Funktionale Programmierung, Git, Gradle, J2EE, Java SE, Java (allg.), Java API for XML Processing (JAXP), Java Architecture for XML Binding (JAXB), Jenkins, Jira, Lua Scripting, Saas, Software engineering / -technik, Softwareentwicklung (allg.), Cloud (allg.), Cloud Computing, System Analyse, System Architektur, System Design, Systems Engineering, Distributed Computing, Ansible, Konfiguration, Systemmigration, Ajax, Google Adwords, Google Analytics, Google Tag Manager, HTML5, JavaScript, Json, Konzeption (IT), Workflows, Requirement Analyse
"Die zielgerichtete und effiziente Arbeitsweise von Herrn Dr. [...] hat das Projekt erfolgreich gemacht."
10/2016 – 11/2018
Tätigkeitsbeschreibung
Designed the architecture of an Elasticsearch-based application for semntic search text analytics.
Implemented an Elasticsarch plugin for linguistic and semantic search and analytics, including custom token filters, query parsers and aggregations (Elasticsearch, Java, Guice).
Designed index structure and continuously optimized search queries to ensure high quality results with low latency.
Designed and implemented customer-specific autocomplete functionality to increase the effectiveness of the semantic search and improve the user experience.
Analyzed the performance of an Elasticsearch cluster in respect to memory and CPU consumption at high load and optimized its configuration
Architekturvisualisierung, Named-entity recognition (NER), Natural Language Processing, Text Mining, Text-Extraction, Textklassifikation, Hibernate (Java), J2EE, Java SE, Java (allg.), Java API for XML Processing (JAXP), Java Architecture for XML Binding (JAXB), Java-Frameworks
"Herr Dr. [...] hat als Lead Software Architect maßgeblich zur Qualität unseres Software Produkts beigetragen."
9/2015 – 6/2019
TätigkeitsbeschreibungDesigned the architecture and led the development of a component-based Cognitive Computing Platform for fast and reliable enterprise applications with an integrated understanding for data and information of all kind: from deep understanding of individual languages (on the level of morphology and syntax), utilization of semantic models and ontologies as well as all state-of-the-art algorithms of machine learning (deep learning, super-vised learning for classifi-cation and clustering and predictive analytics).
Eingesetzte QualifikationenBig Data, Data Mining, Datenanalyse, Predictive Analytics, Continuous Delivery, DevOps, Continuous Integration, Deeplearning4j, Maschinelles Lernen, Neuronale Netze, Apache Spark, Mustererkennung, Named-entity recognition (NER), Natural Language Processing, Spracherkennung, Text Mining, Text-Extraction, Textklassifikation, Linux (Kernel), Ubuntu, Agile Methodologie, Confluence, Projektleitung / Teamleitung (IT), Projektmanagement (IT), Release-Management, Apache, Apache HTTP Server, Apache Tomcat, Jetty, Load Balancing, Nagios, Nginx, Enterprise Service Bus, Fehleranalyse, Softwareanforderungsanalyse, Software Architecture, Software Design, Apache Maven, Bash Shell, Docker, Git, Gradle, J2EE, Java SE, Java (allg.), Java-Frameworks, Jenkins, Jira, Software engineering / -technik, Softwareentwicklung (allg.), Cloud (allg.), Cloud Computing, Serviceorientierte Architektur, System Analyse, System Architektur, System Design, Distributed Computing, Konfiguration, Systemmigration, Ajax, Amazon Web Services (AWS), RDF (Resource Description Framework), RDFS (Resource Description Framework Schema), Web Entwicklung, Web Services, Workflows, Requirement Analyse
Qualifikationen
Projekt‐ & Berufserfahrung
10/2018 – 6/2019
Tätigkeitsbeschreibung
Designed and implemented a web application for text analysis and classifi-cation of news articles relevant to the business case of the client. Used ex-tensively Elasticsearch, Scala, Apache Spark, scikit-learn, python, AngularJS.
Gathered, cleaned, prepared and evaluated training data for classification.
Continuously optimized the classification model using a feedback loop.
Spezialeffekte, Data Science, Big Data, Data Mining, Scikit-learn, Apache Spark, Python, Scala
9/2017 – 3/2019
Tätigkeitsbeschreibung
Designed the overall cloud architecture of a solution for semantic advertisement targeting based on AWS, Elasticsearch and docker.
Designed and implemented a semantic matching algorithm for advertise-ment targeting based on Natural Language Processing and deep learning.
Designed and implemented a low-latency scalable web service to deliver the results of the matching algorithm based on Ratpack and RxJava and running on several EC2 nodes in AWS.
Designed the index structure and optimized Elasticsearch queries to enable fast communication between the distributed components.
Configured and maintained the Elasticsearch cluster to ensure high availa-bility and scalability.
Configured Filebeat and Elasticsearch to monitor the application logs and performance.
Data Science, Big Data, Business Intelligence (BI), Data Mining, Datenanalyse, Administration von Datenbanken, ETL, Continuous Delivery, Configuration Management, Continuous Integration, Keras, Logistische Regression, Maschinelles Lernen, Scikit-learn, Apache Spark, Mustererkennung, Named-entity recognition (NER), Natural Language Processing, Spracherkennung, Text Mining, Text-Extraction, Textklassifikation, Debian Linux, Linux (Kernel), Ubuntu, Scrum, Apache, Apache HTTP Server, Jetty, Nginx, Enterprise Architect (EA), Objektorientierte Analyse (OOA), Objektorientierte Design (OOD), Objektorientierte Software-Entwicklung, Software Architecture, Software Design, Apache Maven, Application Development, Backend, Bash Shell, Reactive Programming, Funktionale Programmierung, Git, Gradle, J2EE, Java SE, Java (allg.), Java API for XML Processing (JAXP), Java Architecture for XML Binding (JAXB), Jenkins, Jira, Lua Scripting, Saas, Software engineering / -technik, Softwareentwicklung (allg.), Cloud (allg.), Cloud Computing, System Analyse, System Architektur, System Design, Systems Engineering, Distributed Computing, Ansible, Konfiguration, Systemmigration, Ajax, Google Adwords, Google Analytics, Google Tag Manager, HTML5, JavaScript, Json, Konzeption (IT), Workflows, Requirement Analyse
10/2016 – 11/2018
Tätigkeitsbeschreibung
Designed the architecture of an Elasticsearch-based application for semntic search text analytics.
Implemented an Elasticsarch plugin for linguistic and semantic search and analytics, including custom token filters, query parsers and aggregations (Elasticsearch, Java, Guice).
Designed index structure and continuously optimized search queries to ensure high quality results with low latency.
Designed and implemented customer-specific autocomplete functionality to increase the effectiveness of the semantic search and improve the user experience.
Analyzed the performance of an Elasticsearch cluster in respect to memory and CPU consumption at high load and optimized its configuration
Architekturvisualisierung, Named-entity recognition (NER), Natural Language Processing, Text Mining, Text-Extraction, Textklassifikation, Hibernate (Java), J2EE, Java SE, Java (allg.), Java API for XML Processing (JAXP), Java Architecture for XML Binding (JAXB), Java-Frameworks
9/2015 – 6/2019
TätigkeitsbeschreibungDesigned the architecture and led the development of a component-based Cognitive Computing Platform for fast and reliable enterprise applications with an integrated understanding for data and information of all kind: from deep understanding of individual languages (on the level of morphology and syntax), utilization of semantic models and ontologies as well as all state-of-the-art algorithms of machine learning (deep learning, super-vised learning for classifi-cation and clustering and predictive analytics).
Eingesetzte QualifikationenBig Data, Data Mining, Datenanalyse, Predictive Analytics, Continuous Delivery, DevOps, Continuous Integration, Deeplearning4j, Maschinelles Lernen, Neuronale Netze, Apache Spark, Mustererkennung, Named-entity recognition (NER), Natural Language Processing, Spracherkennung, Text Mining, Text-Extraction, Textklassifikation, Linux (Kernel), Ubuntu, Agile Methodologie, Confluence, Projektleitung / Teamleitung (IT), Projektmanagement (IT), Release-Management, Apache, Apache HTTP Server, Apache Tomcat, Jetty, Load Balancing, Nagios, Nginx, Enterprise Service Bus, Fehleranalyse, Softwareanforderungsanalyse, Software Architecture, Software Design, Apache Maven, Bash Shell, Docker, Git, Gradle, J2EE, Java SE, Java (allg.), Java-Frameworks, Jenkins, Jira, Software engineering / -technik, Softwareentwicklung (allg.), Cloud (allg.), Cloud Computing, Serviceorientierte Architektur, System Analyse, System Architektur, System Design, Distributed Computing, Konfiguration, Systemmigration, Ajax, Amazon Web Services (AWS), RDF (Resource Description Framework), RDFS (Resource Description Framework Schema), Web Entwicklung, Web Services, Workflows, Requirement Analyse
Ausbildung
Saarland University
RWTH Aachen
Über mich
Design, implementation and continuous optimization of systems for Information Retrieval and Data Analytics, adaptation to use case specific requirements
Implemntation of algorithms for Natural Language Processing, Text Mining an Entity Recognition. Integration of these algorithms in existsing search engies as plugins (Elasticsearch, Apache Solr)
Installation and configuration of development and production environments for search engine-based applications including data modelling and query optimization.
Selection, cleaning and automatic labeling of training data for machine learning models.
Strong communication and leadership skills
Ability to quickly adapt new technologies and work also outside core
competencies
Weitere Kenntnisse
- Elastic Stack
- Apache Lucene
- Apache Solr
Cloud-Technologies
- AWS
- Docker
- Ansible
Artificial Intelligence Technologies:
- Text Mining: Statistical, linguistic and dictionary-based approaches
- Machine Learning / Deep Learning
- Information Retrieval
- Classification / Clustering
Programming Languages:
- Java, Scala, Groovy, PHP
IDEs:
- IntelliJ, Eclipse
Build- / Delivery- / Monitoring-Tools:
- Gradle, Gitlab, Ant, Maven, Jenkins, Nexus, Nagios
Databases
- MySQL
- Postgres
Web Servers/Frameworks:
- Ratpack, Spring MVC, Spring Boot
- Apache Tomcat, Jetty, Nginx
- HTML, CSS, Javascript
- JSP
- XML, XSL, XSLT
Persönliche Daten
- Deutsch (Fließend)
- Englisch (Fließend)
- Bulgarisch (Muttersprache)
- Kroatisch (Grundkenntnisse)
- Europäische Union
- Schweiz
Kontaktdaten
Nur registrierte PREMIUM-Mitglieder von freelance.de können Kontaktdaten einsehen.
Jetzt Mitglied werden