I'm a scientific ML leader and entrepreneur with a background in theoretical physics. I co-founded the Toronto-based biotech ProteinQure, where I lead the scientific ML team and help build a ML-driven platform for protein and peptide therapeutics (think 3D CAD for molecules). I also co-founded the Quantum Open Source Foundation (QOSF).
My work focuses on generative models for proteins and peptides, molecular property prediction, multi-property optimization, and scalable production ML systems for drug discovery. At ProteinQure, I work closely with a multidisciplinary team on proprietary ML models for peptide drug delivery and discovery, spanning model development, optimization, experimental validation and real-world experimental integration.
Technically, I spend time on evolutionary algorithms (using deap), Bayesian optimization, diffusion-based generative models (e.g. RFDiffusion, BindCraft), and custom ML tooling for scientific workflows. My MSc research explored learning curves of quantum kernel machines, using quantum–classical hybrid models built with built with PennyLane and TensorFlow Quantum.
Quick facts:
- 💬 Ask me about scientific ML, protein design, drug discovery, Python, quantum computing, and open-source software
- 📫 Talk to me via hello@markfingerhuth.ai
- ⚡ Fun fact: I like climbing frozen waterfalls in the middle of winter.
Snapshot:
- 💻 My current favourite open source project is Polaris - Benchmarks for AI models in drug discovery
- 🌱 I’m currently learning: modular synthesis, Vietnamese, trad climbing
- 👯 I’m looking to collaborate on Protein Drug Discovery and Quantum Open Source Software
- ⌨️ My work setup consists of: Moonlander MK 1 split keyboard & Kensington SlimBlade Trackball
- 🖨️ I’m currently 3D printing parts for my camper van
- 🎮 I’m currently playing Split Fiction
- 🚐 I’m currently practicing for a triathlon and making music on my modular synthesizer