Vitaly Kurin

Oxford, England, United Kingdom

Join Prog.AI to see contacts

Summary

🤩

Rockstar

🎓

Top School

Vitaly Kurin is a research-focused machine learning engineer with 11 years of experience building RL and learning-from-demonstration systems, currently working on autonomous driving and drug-discovery problems at NVIDIA and Isomorphic Labs. He holds a DPhil candidacy at the University of Oxford and has research internships at DeepMind, Microsoft Research, Facebook AI, and NVIDIA, bringing strong academic rigor to applied industry research. His contributions to notable open-source projects like Theano and the NetHack Learning Environment demonstrate deep backend and testing expertise, including adding core numerical routines and expanding environment test coverage. Previously he helped operationalize in-house learning libraries at Latent Logic and has hands-on experience improving solver heuristics and graph-RL systems. Colleagues value him for blending low-level algorithmic skill with production-minded engineering, and for a rare mix of foundations (applied math background) and practical system work across robotics, simulation, and ML infrastructure.

11 years of coding experience

7 years of employment as a software developer

DPhil (PhD), Computer Science, DPhil (PhD), Computer Science at University of Oxford

Master of Science (M.Sc.), Media Informatics, Master of Science (M.Sc.), Media Informatics at RWTH Aachen University

Bachelor's degree, Bachelor's degree at Moscow state institute of international relations

Lomonosov Moscow State University

English, French, Chinese, Russian, German

Stackoverflow

Stats

193reputation

9kreached

8answers

2questions

Github Skills (24)

pytest10

python10

operation10

testing10

gymnasium10

tensorrt10

openai-gym10

numpy10

tensorflow10

tensor10

theano10

machine-learning9

linear-algebra9

refactoring9

2d6

Programming languages (10)

ShellC++CSCSSJavaScriptZigLuaHTML

Github contributions (5)

facebookresearch/nle

Sep 2020 - Dec 2020

The NetHack Learning Environment

Role in this project:

Back-end Developer & QA Engineer / Test Automation Engineer

Contributions:41 reviews, 37 commits, 22 PRs in 2 months

Contributions summary:Vitaly primarily focused on enhancing the NetHack Learning Environment, specifically by adding functionality for wizard mode and implementing a wizkit for item testing. They added new testing features and also added additional actions. Furthermore, the user refactored and expanded the test suite to include a wider range of test cases, including tests for seed interface and environment rollouts. Their contributions involved modifications to the core environment, action definition, and test files, improving functionality and test coverage.

multiagent-reinforcement-learninggame-aireinforcement-learningmahjongmachine-learning

Theano/Theano

Mar 2016 - Aug 2016

Theano was a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It is being continued as PyTensor: www.github.com/pymc-devs/pytensor

Role in this project:

Back-end Developer

Contributions:7 commits, 2 PRs, 16 comments in 5 months

Contributions summary:Vitaly primarily contributed to the Theano library's core functionality. Their work included refactoring code, specifically moving and modifying functions like `softsign`. The user added the `tensorsolve` function to the library, including tests for its functionality and type upcasting. They also added a deprecation warning for a moved function to ensure backward compatibility during the transition.

python-librarymathmulti-dimensionalpythonevaluate

Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.

Request Free Trial