Machine Learning Research Engineer • Computational Biology

I build machine learning systems from first principles, reproduce and implement research papers, and develop production-ready software for scientific applications.

My work sits at the intersection of machine learning, computational biology, and software engineering, with a particular interest in models for biological data.

I enjoy turning research ideas into reliable software.

Whether implementing transformer architectures from scratch, building bioinformatics pipelines, or developing end-to-end ML systems, my focus is on understanding the underlying methods and producing implementations that are clean, reproducible, and practical.

Alongside machine learning, I have experience building full-stack applications and cloud-native systems, allowing me to take projects from research prototypes to deployable software.

• 🧬 Foundation models for biology
• 🤖 Transformer architectures and representation learning
• 🔬 Computational biology and genomics
• 📊 Machine learning for biomedical data
• 🚀 Open-source implementations of modern ML methods

A PyTorch implementation of the scGPT architecture for single-cell transcriptomics, built to understand every component of the model and its training pipeline.

An end-to-end machine learning workflow for cancer prognosis using transcriptomic data, covering preprocessing, feature engineering, model development, and evaluation.

Research-oriented implementations of transformer architectures, attention mechanisms, embeddings, and training pipelines built from first principles.

• Foundation Models
• Machine Learning
• Deep Learning
• Representation Learning
• Computational Biology
• Bioinformatics
• Scientific Machine Learning
• AI for Healthcare

Machine Learning

PyTorch • Transformers • Scikit-learn • NumPy • Pandas

Computational Biology

Single-cell Analysis • RNA-seq • Scanpy • AnnData • Genomics

Software Engineering

Python • Rust • TypeScript • JavaScript • C

Infrastructure

Linux • Docker • Kubernetes • PostgreSQL • GitHub Actions

Full-Stack Development

FastAPI • Django • React • Next.js

"What I cannot create, I do not understand." — Richard Feynman

I believe strong engineering accelerates good research. Building models from first principles, reproducing published work, and developing reliable software are the foundations of meaningful progress in machine learning.

• 💼 Linkedin
• 🌐 Portfolio (coming soon)
• 📫 Open to Research Engineer, Applied ML Engineer, and Computational Biology opportunities.