Home

My name is Konstantin Selivanov. I am a machine learning engineer and researcher.

• LinkedIn: https://www.linkedin.com/in/selivanov

• GitHub: https://github.com/c0stya

My lifelong focus has been on representation learning and deep learning. As the first machine learning engineer at several startups, I contributed to their successful exits, with some backed by Google Ventures and Sequoia Capital for over $100 million. Feel free to reach out to me.

Interests

• Representation Learning: embeddings, contrastive learning, and information retrieval.

• Natural Language Processing: large language models (LLMs).

• Generative Models: autoencoders, normalizing flows, and diffusion models.

• Sequential Models: rnns, transformers, state-space models.

I value minimalism and efficiency. My primary programming languages are Python, C, and Shell. I have been a Linux user for over 20 years. I am passionate about mathematics and philosophy.