Machine Learning and Data Scientist with a Bachelor of Science from the University of Copenhagen (DIKU). Experienced in the development of data pipelines, analytical models, and visualization frameworks within industrial and regulated environments. Technical expertise includes deep learning, high-performance computing, and statistical modeling, with a focus on transforming complex datasets into actionable operational insights.
- Programming Languages: Python (PyTorch, NumPy, Pandas, TensorFlow), C, SQL, R
- Machine Learning & Analytics: PyTorch Lightning, Scikit-Learn, XGBoost, MLflow, Time-series analysis, Anomaly detection
- Data Engineering & Visualization: ETL pipelines, Alteryx, Power BI, Matplotlib, Plotly, Grafana, SquaredUp
- Systems & DevOps: Linux/UNIX, Git, Docker, CUDA, OpenMP, MLOps principles, REST APIs
January 2024 – January 2026
- Developed Python-based analytics tools for operational insights in IT/OT environments.
- Engineered SQL data models and automated data preparation workflows for large-scale industrial reporting.
- Conducted statistical analysis on incident and root-cause trends to drive infrastructure reliability.
- Implemented monitoring solutions integrating SCOM, SquaredUp, and Grafana for critical infrastructure.
Hidden Markov Model for Visual Attention Analysis
Developed a comprehensive Hidden Markov Model (HMM) to simulate and analyze visual attention patterns using neural spike data.
- Implemented forward simulation algorithms to generate synthetic neural activity.
- Designed exact inference via variable elimination and message passing algorithms.
- Applied approximate inference using logistic regression and implemented a hard-assignment EM algorithm for parameter learning.
- Validated the framework across both simulated and real-world neural datasets.
Collaborative research project with NASA and the University of Copenhagen (DIKU and IGN) focused on Greenland’s coastline.
- Developed a U-Net architecture for high-resolution segmentation of satellite imagery.
- Achieved a spatial accuracy of 0.87 IoU (Intersection over Union).
- Optimized inference speed for large-scale geospatial datasets.
Conducted in collaboration with the Danish Meteorological Institute (DMI) to automate the validation of sensor data.
- Designed and benchmarked three distinct machine learning architectures to detect faulty sensor readings.
- Documented and analyzed DMI's ETL pipelines and manual validation processes.
- Developed a solution to reduce manual overhead for climatologists through automated anomaly detection.
Developed predictive maintenance tools for manufacturing environments.
- Built an LSTM-based (Long Short-Term Memory) recurrent neural network for early equipment failure detection.
- Integrated models with OPC-UA data streams for real-time signal monitoring and processing.
Personal project focused on the fundamentals of computational efficiency in neural networks.
- Implemented a Multi-Layer Perceptron (MLP) from scratch in C.
- Utilized OpenMP for CPU multi-threading and CUDA for GPU acceleration to optimize training performance.
University of Copenhagen (2019 – 2023)
- Key Coursework: Algorithms & Data Structures, High Performance Programming, Probability Theory & Statistics, Linear Algebra, Advanced Deep Learning, Models for Complex Systems.
- Specialization: Medical Image Analysis, Lebesgue Integral & Measure Theory, and Satellite Segmentation.
- Teaching Assistant: Empirical Methodologies & Theory of Science (2021 – 2023). Guided students through research methodology and academic reasoning.
- Teaching Assistant: Programming Intro Course (2021). Supported first-year students in Python and programming fundamentals.
- Student Mediator: Represented the Machine Learning & Data Science program at the Department of Computer Science (DIKU), coordinating outreach and curriculum communication.