Petr Karnakov

pkarnakov@gmail.com

linkedin.com/in/pkarnakov

github.com/pkarnakov

CV

Research scientist with over 10 years of experience in software engineering, high-performance computing, and machine learning. Background spans academic research at ETH Zurich and Harvard University and industry at DeepL, with expertise in numerical methods, physics simulations, and production ML systems based on LLMs and vision-language models. List of publications.

Research Projects

ODIL

ODIL (Optimizing a DIscrete Loss) is a method and Python framework for solving inverse problems for partial differential equations, which is orders of magnitude faster than PINN (physics-informed neural networks). Article about the method.

Inverse design: body from flow

Demo: Poisson

Demo: Wave

Demo: Heat

Aphros

Distributed multiphysics solver in C++ with MPI for simulating multiphase flow with bubbles and electrochemical reactors. The solver performed the largest simulations of foaming by breakup and mixing of air in water. Article about foam simulations.

Bubble coalescence

Cheerios effect

Bubble splitting device

Foaming by mixing of air in water

Water electrolysis: multiphysics model

Demo: Drops

Demo: Electrolysis

Demo: Gallery

Other Projects

autodiff

Automatic differentiation framework in C++ with GPU support through OpenCL.

Reverse mode

AM205

Visual materials for a class on numerical methods that I lectured in 2022.

Removing day-night cycle from video using PCA | slide

Sound of the wave equation | slide

ptoy

Game with particles and portals in C++.

Web version

TinyOS

Prototype operating system in x86 assembly for a school competition in 2008.

Screencast