18.12.2024 aktualisiert
80 % verfügbar
Sr Data-Scientist, ML/DS Big Data (Spark, Data-mining, Text-mining, Web-mining, Python, R, MongoDB)
München, Deutschland
Deutschland +2
Dipl.-MathematikerSkills
LinuxBiostatistikAutonomes FahrenAutonomous Carsneuronale NetzeR StatisticsComputer VisionData ScientistMongoDBAutomatisierungPythonC++Daten AnalystData MiningAttribution ModelingBig Data Analyticspytorch
I am a data scientist (MS math) from Munich with strong IT-skills and experience in:
You’ll catch my extra attention, if your project targets one or more of:
- Datamining / Textmining / Webmining (see dooblet.com or check this screencast: https://www.youtube.com/watch?v=mW_D51kGN2o)
- Attribution Modeling (GAM, ARIMA, ARMA, etc)
- data analysis (R, Python), modeling, forecasting
- Web-Applications for data analysis
- Explorative data analysis
- Biostatistics: proteomics, epigenomics (other *omics are also very welcome!)
You’ll catch my extra attention, if your project targets one or more of:
- Machine learning, deep learning (esp. LSTM)
- Large-scale parallelism (“deep parallelism”)
- Analysis/modeling of huge amount of data (BigData)
- Bioinformatics, Biostatistics, Pharma, Psychology, Finance
- Go (Golang), Scala, TensorFlow/Theano
Sprachen
DeutschverhandlungssicherEnglischverhandlungssicherRussischMuttersprache
Projekthistorie
- Mentoring for Advanced Analytics
- Multivariate Analysis, Correspondence Analysis, Cause and Effect Analysis, Factor Analysis, ICA, PCA, etc.
Tools: R / RStudio, Python / PyTorch
• building Data Lake from scratch
• automated Spark batch-processing
• setting up full cycle GitLab CI and GitLab Flow
• Spark-based data depersonalization and historization
• defining the Software Developer Guide for a team
Tools: Spark, Hive, Hadoop, Python, PySpark, GitLab, Docker, Docker Hub, Apache Zeppelin, Hortonworks, Nexus, git, Linux toolset
• automated Spark batch-processing
• setting up full cycle GitLab CI and GitLab Flow
• Spark-based data depersonalization and historization
• defining the Software Developer Guide for a team
Tools: Spark, Hive, Hadoop, Python, PySpark, GitLab, Docker, Docker Hub, Apache Zeppelin, Hortonworks, Nexus, git, Linux toolset
Highlight: I am the author of geo-localization technology used by Telefonica
• Location Intelligence derived from Big Data
• Geo-localization of subscribers based on anonymized low-level event data produced within mobile network
• Big Data analysis of network event data using AWS EMR and Spark
Tools: Scala, Spark, Python, R, Zeppelin, Hive SQL, Hadoop, S3, AngularJS, AWS EMR, EC2, Docker, AWS Linux, OpenStreetMap (OSM)
• Location Intelligence derived from Big Data
• Geo-localization of subscribers based on anonymized low-level event data produced within mobile network
• Big Data analysis of network event data using AWS EMR and Spark
Tools: Scala, Spark, Python, R, Zeppelin, Hive SQL, Hadoop, S3, AngularJS, AWS EMR, EC2, Docker, AWS Linux, OpenStreetMap (OSM)