Artem Pulkin

me

[ɐrˈtsʲɡm]

Researcher, data scientist, software engineer

πŸ“§ gpulkin@gmail.com 🌐 pulk.in 🏠 Amsterdam NL πŸ‡³πŸ‡±

πŸ” jobs: researcher, ML scientist, research engineer, data scientist, software engineer

Currently

Developing innovative machine learning approaches to engineer electronic materials and molecules addressing modern society challenges

Expertise

Computational condensed matter, quantum chemistry, numerical materials science, machine learning, many-body physics, research code development.

Education πŸŽ“

2012-2017 Docteur Γ¨s Sciences EPFL in physics Lausanne CH πŸ‡¨πŸ‡­ Specialized on: numerical electronic structure, quantum simulations. Thesis: Electronic Transport in 2D Materials with Strong Spin-orbit Coupling (03/2017); supervisor: Oleg Yazyev

2010-2012 Master of Science Chalmers in applied physics GΓΆteborg SE πŸ‡ΈπŸ‡ͺ Thesis: Spintromechanical Aspects of Charge Transport in Nanostructures (06/2012); supervisor: Robert Shekhter

2006-2010 B.Sc. in Physics cum laude V.N. Karazin’s State University Kharkiv UA πŸ‡ΊπŸ‡¦

Training

Coursera: Machine Learning from Stanford University

Experience πŸ”¬

Apr'19-Apr'22 Researcher @ QuTech Delft university of technology NL πŸ‡³πŸ‡±

As a part of a multi-disciplinary team of condensed matter and quantum nanoscience researchers I carried out a long-term ambitious research of materials for application in future electronics. I developed and implemented novel numerical approaches to solving materials in the open-source python package miniff.

Jul'17-Mar'19 Postdoc @ Caltech US πŸ‡ΊπŸ‡Έ

In collaboration with prof. Garnet Chan quantum chemistry group from Caltech I developed and implemented a ground breaking computational many-body quantum chemistry framework to model two-dimensional crystalline materials as a part of pyscf python package.

Oct'12-Apr'17 Doctoral assistant @ EPFL CH πŸ‡¨πŸ‡­

I discovered a new class of electronic band structure effects in two-dimensional transition metal dichalcogenides using a stack of high-performance distributed numerical tools developed by myself in python, C, Matlab, and Fortran.

Jun'12-Aug'12 Research assistant @ Seoul National University, KR πŸ‡°πŸ‡·

I was studying electronic structure of edge states in models of overlapping topological graphene nanoribbons.

Aug'10-Jun'12 Research assistant @ Chalmers, SE πŸ‡ΈπŸ‡ͺ

I was designing a concept of a nanoscale spin-mechanical single-electron transistor (SET).

In numbers

15 publications >500 citations 14 talks

>10 countries

>30 collaborators

Software

More on github/pulkin

miniff miniFF https://gitlab.kwant-project.org/qt/miniff (python, cython)

Simulate molecular dynamics with classical force fields and machine learning. Combines the power of cython, numpy and torch to deliver maximal performance in a high-quality python code.

pyscf pyscf https://github.com/pyscf/pyscf (python, C)

A large collaboration across universities and public companies towards high-performance Quantum chemistry in python. I contributed towards implementing periodic boundary conditions for diagrammatic kernels.

pyteleport pyteleport https://github.com/pulkin/pyteleport

Pause, teleport and resume your python runtime from within the stack. Manipulates cPython memory and bytecode.

dfttools https://github.com/pulkin/dfttools (python)

Parsing and plotting the results of first-principles simulations.

openmx-hks https://github.com/pulkin/openmx-hks (C)

A practical tool to convert the data from a popular density functional theory code into numpy.

micropython https://github.com/pulkin/micropython (C)

A micropython port to a popular cellular network module A9G.

Awards πŸ†

postgraduate πŸ’° Personal Swiss NSF grant to study abroad 80k CHF, 18 months, postdoctoral level (Early Postdoc.Mobility) grant P2ELP2_175281

πŸ’° Personal computing time at national supercomputing facilities (SURF NL) Approximate equivalent of 26k EUR, 24 months project 45873

graduate πŸ₯‡ Olympiad in Physics for University Students (national in Ukraine) – first prize

πŸ… Youth Physicists Tournament (national in Ukraine, team) – multiple prizes

πŸ₯‡ Open Olympiad in Applied Physics (MIPT Moscow) – first prize

πŸ’° Kharkiv City Mayor and Kharkiv State Governor scholarships for gifted youth

high school πŸ₯‡ Dozens of prizes in physics and informatics (olympiads, student projects; top-10 and top-1 in national competitions)

πŸ’° Multiple scholarships

Skills πŸ”¨

Science: quantum condensed matter, first-principles approaches.

Machine learning: supervised learning (DNN, linear fits, logistic fits, SVM); unsupervised learning (PCA/SVD, K-means, anomaly detection); dataset generation, feature extraction, adversarial models; deployment: HPC, heterogeneous environments (GPU+CPU).

Software development in 🐍 Python (7 years): scientific stack: numpy, torch, matplotlib; notebooks; HPC and parallel/distributed/concurrent computing (MPI, OpenMP, multiprocessing, async); performance-driven development with C and cython; styling, testing, documenting, packaging; micropython and python beyond standards (cPython bytecode).

C: HPC and parallel environments (MPI, OpenMP); Lapack; embedded platforms.

Other: β˜• Java, Fortran, Julia, Javascript, Matlab.

Infrastructure: git, CI/CD (Travis, Gitlab-CI, Azure pipelines).

IDEs: Pycharm, vim.

Soft skills: critical analysis, problem solving, communicating (organizing discussions, presenting, paper/grant/documentation writing), full-cycle project management (idea - funding - implementation - reporting), supervision.

Languages

English (proficient), Russian (mother), French (basic), Dutch (basic).

Hobbies

Sports, ✈ travels, cross-stitching, soldering, πŸ”’ lock picking, πŸ•ΉοΈ board and video games, open-source projects.