I am an experienced MLOps engineer, Python developer, and data scientist. With expertise in designing and implementing scalable and robust ML infrastructure, automating ML workflows, and monitoring and optimizing model performance, I can help your organization take your ML projects to the next level.I am currently working for clients in the energy- and insurance industry.
In my free time, my interests include travelling and snowboarding, making music and videos.
Working for clients in the energy and insurance sector on machine learning engineering and cloud architecture tasks.
Development of a Big Data framework for continuous analysis of PV systems data. Roadmapping and realization of data services in the renewable energy sector.
Development of time series analysis and predictive maintenance algorithms for solar power inverters. Ethereum blockchain development for energy management applications.
Algorithm design for time series analysis and forecasting. Collaboration in the LOEWE project "BigEnergy" for the development of scalable algorithms for regenerative power forecasting. Mentoring of students in classes and theses.
Leading a project team for the development of a multi-sensor framework. Application of methods for 3D reconstruction for vehicle environment recognition. Development of image processing algorithms.
Software development of firmware features for sheet-fed offset printing machines.
PhD studies in computer science on time series forecasting techniques for renewable energy generation using techniques from machine learning.
Studies with focus on techniques from image processing and pattern recognition. Applications included prediction of the intention of vulnerable road users.
Master Thesis: Erkennung von Bewegungsmustern nicht geschützter Verkehrsteilnehmer aus der Vogelperspektive.
Courses included fundamentals of electrical engineering and information technology, circuit design and computational intelligence.
Bachelor Thesis: Entwicklung einer dezentralen Datenlogger-Komponente zur zeitlich korrelierten Aufzeichnung verschiedener Datenströme auf FPGA-Basis
Gensler A, Sick B. Probabilistic Wind Power Forecasting: A Multi-Scheme Ensemble Technique With Gradual Coopetitive Soft Gating. In: Proceedings of the 9th IEEE Symposium Series on Computational Intelligence (SSCI17). Honolulu, USA; 2017:1803-1812.
Gensler A, Sick B. Performing Event Detection in Time Series with SwiftEvent: An Algorithm with Supervised Learning of Detection Criteria. Springer Pattern Analysis Applications (PAA). 2017;1(1):1-20.
Gensler A, Sick B. Forecasting Wind Power - An Ensemble Technique With Gradual Coopetitive Weighting Based on Weather Situation. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN16). Vancouver, Canada; 2016:4976-4984.
Gensler A, Sick B, Vogt S. A Review of Deterministic Error Scores and Normalization Techniques for Power Forecasting Algorithms. In: Proceedings of the IEEE Symposium Series on Computational Intelligence (SSCI16). Athens, Greece; 2016:1-9.
Gensler A, Sick B, Pankraz V. An Analog Ensemble-Based Similarity Search Technique for Solar Power Forecasting. In: Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC16). Budapest, Hungary; 2016:2850-2857.
Gensler A, Henze J, Sick B, Raabe N. Deep Learning for Solar Power Forecasting – An Approach Using Autoencoder and LSTM Neural Networks. In: Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC16). Budapest, Hungary; 2016:2858-2865.
Gensler A, Gruber T, Sick B. Blazing Fast Time Series Segmentation Based on Update Techniques for Polynomial Approximations. In: Proceedings of the IEEE 13th International Conference on Data Mining Workshops (ICDMW13). Dallas, USA; 2013:1002-1011.
Gensler A, Sick B. Novel Criteria to Measure Performance of Time Series Segmentation Techniques. In: Proceedings of LWA/KDML: Workshop on Knowledge Discovery, Data Mining and Machine Learning. Vol 2. Aachen, Germany; 2014:29-37.
Gensler A, Gruber T, Sick B. Fast Feature Extraction For Time Series Analysis Using Least-Squares Approximations with Orthogonal Basis Functions. In: Proceedings of the International Workshop on Temporal Representation and Reasoning (TIME15). Kassel, Germany; 2015:29-37.
Gensler A, Sick B, Willkomm J. Temporal Data Analytics Based on Eigenmotif and Shape Space Representations of Time Series. In: Proceedings of the IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP14). Xian, China; 2014:753-757.
Goldhammer M, Doll K, Brunsmann U, Gensler A, Sick B. Pedestrian’s Trajectory Forecast in Public Traffic with Artificial Neural Networks. In: Proceedings of the 22nd International Conference on Pattern Recognition (ICPR14). Stockholm, Sweden; 2014:4110-4115.
Stone T, Birth O, Gensler A, Huber A, Jänicke M, Sick B. Location based learning of user behavior for proactive recommender systems in car comfort functions. In: Lecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft Fur Informatik (GI). Stuttgart, Germany; 2014:2121- 2132.
Python, Matlab, C / C++, Java, Solidity
PyCharm, JupyterLab, MATLAB IDE, Eclipse, Visual Studio
scikit-learn, pandas, numpy, Matlab Toolboxes, OpenCV, Qt, Tensorflow, Keras, Spark, Qt
MS-SQL, SQLite
Jenkins, Git, Docker, Subversion, Doxygen, CMake, AWS, Shell Scripting
Gensler, André. Wind power ensemble forecasting. PhD thesis, kassel university press, University of Kassel, 2018.