Building Intelligent Systems Across Data, Energy & Physical Infrastructure
- 🎓 MSc in Building Energy Design (Aalborg University) · BSc in Architectural Technology & Construction Management · AS in Computer Information Systems
- ⚡ Energy & Data Analyst — background in large-scale time-series data from building and utility systems
- 🔬 My work sits at the intersection of building physics, data engineering, and applied machine learning
- 🌍 Based in Aalborg, Denmark — open to opportunities in Applied AI, Backend Engineering, Data Engineering, IoT, and Industrial/Robotics Software
|
🔥 ThermOps Physics-informed + ML-powered diagnostics platform for district heating systems. Ingests hourly sensor data, builds a thermal twin per building, and runs anomaly detection (autoencoder pipeline + root-cause attribution) to quantify energy waste and issue ranked, auditable recommendations.
|
📈 FlexTrade AI Full-stack energy intelligence terminal for power market operators and traders — live electricity prices, weather, gas/carbon analytics, a GIS infrastructure map, derivatives, a trading simulator, risk monitoring, and an AI advisor across Denmark, Germany, ERCOT, and JEPX.
|
I'm currently expanding from backend/data engineering into Applied AI, autonomous systems, and robotics software.
🧠 Applied AI Engineering
LLMs • RAG • Embeddings • Vector Search • Tool Calling • Structured Outputs • Model Evaluation
Learning how to build AI applications that interact with real data, APIs, tools, and persistent system state.
🤖 Agentic AI & Autonomous Systems
AI Agents • Multi-Agent Systems • Planning • Memory • Knowledge Graphs • Agent Orchestration • Failure Recovery
My focus is on moving beyond one-shot AI applications toward systems that can:
Plan → Execute → Observe → Verify → Recover → Remember → Continue
⚙️ AI Systems Engineering
Distributed Systems • Event-Driven Architecture • Queues • Caching • Observability • Fault Tolerance • MLOps
Learning how to make AI systems reliable, persistent, observable, and deterministic enough for real-world software.
🧠 Machine Learning
PyTorch • Deep Learning • Time-Series ML • Feature Engineering • Model Evaluation • Anomaly Detection
Strengthening the ML foundation underneath the AI systems I build.
🛸 Robotics & Edge AI
Computer Vision • Embedded AI • Sensor Fusion • Autonomous Navigation • Edge Computing • Robotics Software
Exploring how AI moves from cloud applications into physical systems that perceive and interact with the real world.
🔌 Embedded & Hardware Systems
Raspberry Pi • Sensors • Cameras • Serial Communication • Linux • Hardware/Software Integration
Learning how software interfaces with sensors, controllers, embedded computers, and robotic platforms.
|
Designing a persistent AI system capable of working on long-running objectives instead of isolated prompts. Core ideas
Execution loop
|
Reverse-engineering a low-cost drone as a robotics platform for learning how intelligent software interacts with the physical world. Exploring
System concept
|