👨🎓 M.S. Medical Biotechnology from KTH | 🧬 AI Genomics Research at Stanford | 💻 Full-Stack Developer
I'm a passionate technologist with a strong software engineering and biotechnology background. Currently, I'm working as a full-stack developer at UX Stream and applying AI models to whole-genome sequencing data in Stanford University's Snyder lab. My diverse experience spans from founding an IT consultancy to developing low-latency streaming solutions for mobile devices.
- Classifying diseases using AI models on whole-genome sequencing data
- Building pipelines for high-throughput analysis with graph neural networks
- Integrating proteomics with sequencing data through pQTL-analysis
-
- AI models for Annotated VCF files through ANNOVAR
- Improved, interpretable disease classification through graph neural networks of gene-gene interactions.
-
HEAL (Hierarchical Estimate from Agnostic Learning)
- Machine learning-based genome analysis and risk prediction framework
- Supports mutation burden matrix analysis (CSV format)
- Outputs disease gene lists, genetic risk prediction models, and prediction performance summaries
-
Full-Stack Software Engineer at UXStream
- Developed low-latency streaming solutions for mobile devices
- Reduced latency by 75% over 5G networks
-
Founder and Software Engineer at Appberg
- IT consultancy firm with 30+ clients
- Developed various SaaS platforms and mobile apps
- Stanford University School of Medicine - Master's Thesis Applying AI Models to Whole-Genome Sequencing Data
- KTH Royal Institute of Technology - M.S. in Medical Biotechnology, B.S. in Chemical Engineering
- Languages: Rust, Python, TypeScript, JavaScript, Kotlin, Swift, Objective-C, R, MATLAB
- Frameworks: Scikit-Learn, PyTorch, Tensorflow, React / React Native, Flatbuffers, Tokio
- Developer Tools: Git, Docker, Slurm, Azure, AWS, Firebase
- LinkedIn: linkedin.com/in/mkjellbe
- Email: mkjellbe@stanford.edu
- Phone: +46 736 72 78 77
⭐️ From martinappberg