Machine Learning Engineer

• Jun 2023 - Present

Bio-image Processing and Data Analysis: 1 .AI-Driven Drug Discovery - Leveraged image-based profiling and segmentation techniques using AI/ML to advance condensate drug discovery processes. 2 .Omics Pipelines for Drug Analysis - Spearheaded the integration of multi-modal omics pipelines with Neo4j knowledge graphs, delivering vital support for comprehensive drug analysis. 3. Advanced Knowledge Graph ETL - Orchestrated a cutting-edge ETL process for knowledge graphs, paving the way for innovative analytics, including community deduction and personalized page rank. This enhanced the targeting of gene lists in condensate biology. 4. Knowledge Graph Embedding - Masterminded node embedding strategies for knowledge graphs, employing best-in-class methods such as Node2vec, GraphSAGE, and Graph Neural Networks. 5. Machine Learning for Knowledge Graphs - Devised and deployed ML pipelines tailored for link prediction and multi-label classification within knowledge graph networks. Tools utilized include logistic regression, SVM, XGBoost and some other best machine learning method. Show less

Machine Learning Research Project

• Nov 2022 - Present

Motion Capturing & Data Analysis in Physiotherapy: Development of prototypical system with which recognised exercises in real time and the movement execution is evaluated computer-aided 1. Conducted a literature review on the latest research, methods, models, and data sets for movement analysis and evaluation in physiotherapy and sport. 2. Acquired MoCap data for testing the algorithms. 3. Processed and cleaned the MoCap data using relevant data processing techniques. 4. Developed a baseline machine learning model for haptic feedback prediction. 5. Designed and implemented an alternative machine learning model to compare and validate different approaches to data analysis. 6. Compared and validated different approaches to data analysis to determine the most effective techniques for haptic feedback prediction. 7. Derived requirements for a user interface (UI) that is suitable for both physiotherapists and patients, with the aim of simplifying the data analysis process. Show less

Student

• 2018 - Present

Studentische Hilfskraft(SHK)-AI and Machine Learning Research and Development

• Feb 2022 - Feb 2023

Multi-task learning for holistic data-driven models of engineering systems.1- Demonstrated expertise in implementing neural networks((ANN. CNN, RNN, GNN, Multi-gate mixture of Expert) using standard frameworks like PyTorch/TensorFlow.2- Utilized object-oriented programming in Python and/or C++ for the project.3-Generated synthetic data using statistical methods to create machine learning models for analysis.4-Conducted research and analysis on Single Task Learning (STL) and Multitask-Learning (MTL) machine learning models for MultiOutput Regressor problems.5-Investigated the relationship between tasks and identified the best measurement for task relationships.6- Designed a research problem and investigated the space of the engineering domain for MTL approaches on datasets. and Try to Answer the Research problem question. a)-Which amount of data investigating (Example: from 10 to 100 data points per task or from 1.000 to 100.000 or …)? b)-Which amount of tasks are investigating (Example: from 2 to 4 data points per task or from 10 to 100 or …)? c)-Which cases for the task relationship are investigated? d)-Compare model evaluation analysis with sparse data and non-sparse data.7- Conducted data preprocessing tasks such as cleaning, feature importance, skewness, data reduction, and data transformation to prepare the machine learning model pipeline.8-Reviewed large amounts of information to discover trends and patterns, and compared synthetic and real datasets. Show less

Mentor

• Feb 2021 - Present

Machine Learning Research Intern

• Sep 2022 - Jun 2023

Wissenschaftliche Hilfskraft/Research Assistant-Machine Learning Research and Algorithms Development

• Jan 2023 - Mar 2023

Data Compression of Particle-In-Cell Simulation Outputs 1. Implement a PIConGPU plugin for data compression of 6D phase space and integrate it into the simulation workflow. 2. Explore and evaluate different compression techniques such as lossless, lossy, and predictive coding to achieve high compression rates while maintaining sufficient accuracy. 3. Develop a post-processing pipeline that uses a neural network to reconstruct the compressed data and generate visualizations. 4. Investigate the effectiveness of different neural network architectures and training techniques for the post-processing task. 5. Design an automated machine learning workflow that includes data preprocessing, feature selection, and hyperparameter optimization for the neural network model. 6. Use Python and relevant libraries such as scikit-learn and PyTorch for implementation and evaluation. 7. Compare the performance of the compressed data against the original data in terms of accuracy, storage size, and computational efficiency. 8. Conduct experiments to evaluate the scalability of the proposed approach for large-scale simulations and identify potential bottlenecks. 9. Write clear and concise documentation of the code and methods for reproducibility and future reference. Show less

Certificate of Quantum Excellence-Quantum Machine Learning QGSS2021

• Jul 2021 - Aug 2021

Completed the two-week intensive course provided by IBM Quantum, completing all graded lab work assignments with a final cumulative score above 75%, demonstrating applied understanding and comfort with and about Quantum Computing and Quantum Machine Learning using Qiskit. Grade: 100/100 Completed the two-week intensive course provided by IBM Quantum, completing all graded lab work assignments with a final cumulative score above 75%, demonstrating applied understanding and comfort with and about Quantum Computing and Quantum Machine Learning using Qiskit. Grade: 100/100

Student

• Nov 2020 - Nov 2020

QWorldChallenge2020 Autumn Edition! I learn the basics of quantum programming and computing. Also Developed interesting Quantum computing simulation which is used in further research work. QWorldChallenge2020 Autumn Edition! I learn the basics of quantum programming and computing. Also Developed interesting Quantum computing simulation which is used in further research work.

Quantum2020: A VIRTUAL CONFERENCE

• Oct 2020 - Oct 2020