1000x more efficient fluid simulations for engineers

Fluid simulations are an essential tool in a wide range of industries when designing planes, cars and wind turbines. However, these simulations are extremely computationally expensive, often taking days to weeks to run, critically slowing down design iteration workflows.

Fortunately, recent advances in machine learning research have shown these simulations can be accelerated by up to 1000x, and Vanellus is building these breakthroughs into a commercial fluid solver product.

The Team

Vanellus founder Laurence Cullen relaxing in an office chair.

Laurence Cullen

Previously: Fetch.ai, Sensity, ARM.

Laurence is a machine learning engineer of 6 years who is skilled at rapid prototyping and has taken two startups to seed as a first and second employee. Whilst at Sensity, he led the development of one of the world’s first deepfake detection products from scratch, defining and implementing features in consultation with customers from Reuters and The Guardian. His technical expertise includes computer vision, NLP and full-stack web development.

Vanellus founder Michael Negus.

Dr. Michael Negus

Michael holds a PhD in Applied Mathematics from the University of Oxford. His expertise lies at the interface between mathematics, physics and scientific computing, and in applying recent advances in machine learning to accelerate existing simulation methods.

Supported by:


* indicates required