Sergei Bratchikov is an NLP and RL engineer with 8 years of experience building and aligning large language models, moderation systems, and high-throughput inference pipelines across industry and open-source labs. He designs SOTA detectors for harmful and hallucinated content, automates jailbreak testing to harden model safety, and applies online/offline RL to improve moderation and alignment. His work spans production optimization (vLLM, ONNX, Triton, TensorRT, FP8 quantization) and research-grade tooling—he leads open-source LLM projects and training frameworks with publications including EMNLP 2024. Based in France and trained in applied mathematics at NUST MISIS, Sergei blends rigorous academic grounding with hands-on system engineering and a notable knack for turning adversarial model attacks into stronger, community-facing safety benchmarks.
8 years of coding experience
4 years of employment as a software developer
National University of Science and Technology "MISIS" (Moscow Institute of Steel and Alloys)
Private chat bot on aiogram for limited access to ChatGPT with custom personalities.
Contributions:14 PRs, 92 pushes, 16 branches in 1 year 11 months
aiogrambotchatgpt-apipython
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
Sergei Bratchikov - NLP & RL Engineer at White Circle