Artem Pulkin
[ΙrΛtsΚ²Ι΅m]
Postdoctoral researcher at QuTech TU Delft
π§ gpulkin@gmail.com π pulk.in π Amsterdam NL π³π±
π jobs: researcher, research engineer, data scientist, software engineer
Currently
Developing innovative machine learning approaches to engineer electronic materials and molecules addressing modern society challenges
Expertise
Computational quantum, machine learning, research code development
Education π
2012-2017
Docteur Γ¨s Sciences EPFL in physics Lausanne CH π¨π
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 πΈπͺ
Thesis: Spintromechanical Aspects of Charge Transport in Nanostructures (06/2012);
supervisor: Robert Shekhter
2006-2010
B.Sc. in Physics cum laude V.N. Karazinβs State University Kharkiv UA πΊπ¦
Research π¬
2019-now
Postdoc @ QuTech and Kavli Institute of Nanoscience, Delft university of technology NL π³π±
Researching a stack of machine learning tools: deep neural networks DNN, generative models (reverse Monte-Carlo, RMC), adversarial attack approaches in the context of electronic structure/nanoscale atomic dynamics. Developing a DNN/atomic descriptor code for nanoscale dynamics miniff. Discovering novel electronic materials as a part of a multi-disciplinary team of quantum researchers.
Jul'17-Mar'19
Postdoc @ Caltech US πΊπΈ
Developed and implemented a computational many-body quantum chemistry framework to model two-dimensional crystalline materials. Investigated low-energy spectral properties of two-dimensional molybdenum disulphide with numerical modeling.
Oct'12-Apr'17
Doctoral assistant @ EPFL CH π¨π
Carried out a scientific project in the quantum materials modelling domain. Discovered a new class of electronic band structure effects in two-dimensional semiconductors. Collaborated with world-leading experimental groups to prove my findings experimentally.
Jun'12-Aug'12
Research assistant @ Seoul National University, KR π°π·
Aug'10-Jun'12
Research assistant @ Chalmers, SE πΈπͺ
In numbers
15 publications >500 citations 14 talks
>10 countries
>30 collaborators
Software
More on github/pulkin.
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
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
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 π
postgraduate
π° Personal Swiss NSF grant to study abroad
80k CHF, 18 months, postdoctoral level (Early Postdoc.Mobility) grant P2ELP2_175281
π° Personal computing time at national supercomputing facilities (SURF NL) Approximate equivalent of 26k EUR, 24 months project 45873
graduate
π₯ Olympiad in Physics for University Students (national in Ukraine) β first prize
π Youth Physicists Tournament (national in Ukraine, team) β multiple prizes
π₯ Open Olympiad in Applied Physics (MIPT Moscow) β first prize
π° Kharkiv City Mayor and Kharkiv State Governor scholarships for gifted youth
high school
π₯ Dozens of prizes in physics and informatics (olympiads, student projects; top-10 and top-1 in national competitions)
π° Multiple scholarships
Skills π¨
Science: quantum condensed matter, first-principles approaches.
Machine learning: supervised learning, deep neural networks (DNN), dataset generation, feature extraction, generative modelling, adversarial attacks.
Software development in π Python (6 years): numpy, torch, matplotlib; notebooks; HPC and parallel/distributed/concurrent computing (MPI, OpenMP, multiprocessing); 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, β travels, cross-stitching, soldering, π lock picking, πΉοΈ board and video games, open-source projects.