Scientific ML / Computational Biology — biological sequence modeling, foundation models, ML evaluation and research software
PhD in Bioinformatics and ML, studied Biophysics for MSc and BSc
I am a computational biologist and scientific software developer working at the intersection of machine learning, biological data, and research software.
I build computational methods and reusable software for biological R&D, with experience spanning biological sequence modeling, immunoinformatics, omics, and drug-development applications. A recurring focus of my work is evaluating whether new machine-learning methods provide meaningful improvements over strong baselines and translating successful prototypes into reliable scientific workflows and software.
I am particularly interested in foundation models for biology, deep learning for biological sequences and structures, rigorous ML evaluation, and AI-assisted scientific workflows.
- Programming: Python, R; PyTorch and scientific Python ecosystem
- Scientific ML: deep learning, representation learning, biological sequence modeling, benchmarking and model evaluation
- Computational biology: immunoinformatics, protein and RNA sequence analysis, transcriptomics
- Research software: reproducible workflows, testing, APIs, CI/CD, Snakemake and Nextflow
- Current interests: AI for Science, biological foundation models, generative modeling, scientific software, and reliable AI-assisted R&D