Dmitrii Krasheninnikov

Member Of Technical Staff at Anthropic

Stony Stratford, England, United Kingdom
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
🎓
Top School
Dmitrii Krasheninnikov is an AI safety researcher and machine learning engineer with 11 years of experience bridging academic rigor and applied RL/robotics work. Currently a Research Fellow at Anthropic, he completed a PhD in Machine Learning at the University of Cambridge and has a track record of impactful internships and roles at CHAI, SonyAI and The Curious AI Company. His research has produced novel contributions to inverse reinforcement learning, reward aggregation and partially observable RL—papers presented at ICLR and NeurIPS workshops—while also delivering practical systems for robotics and stable deep learning training. Dmitrii combines formal theoretical thinking with hands-on engineering, from memory-efficient bioinformatics algorithms to autonomous ROS vehicles, and is actively seeking ML research roles in academia or industry. An understated strength is his ability to translate misspecified reward models into usable distributions, a thread that links his theoretical and applied work.
code11 years of coding experience
job5 years of employment as a software developer
bookMaster of Science - MS, Artificial Intelligence, Master of Science - MS, Artificial Intelligence at University of Amsterdam
stackoverflow-logo

Stackoverflow

Stats
1reputation
0reached
1answer
0questions
github-logo-circle

Github Skills (14)

reinforcement-learning9
reward9
meta-learning6
python6
lasagne6
theano6
language-model4
machine-learning3
intelligent3
skynet3
ros2
nlp1
cpp1
natural-language-processing1

Programming languages (3)

C++Jupyter NotebookPython

Github contributions (5)

github-logo-circle
Code for the paper "Implicit meta-learning may lead language models to trust more reliable sources"
Contributions:19 reviews, 3 PRs, 116 pushes in 2 years 1 month
language-modelmeta-learning
Maximum Causal Entropy Inverse Reinforcement Learning
Contributions:155 commits, 109 pushes, 4 branches in 1 year 3 months
reinforcement-learninginverse-reinforcement-learning
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