Vladislav Beliaev
RL researcher, founding engineer
8 years training models and shipping them to millions.
now: post-training research on cross-model reasoning.
bets
AGI is a fusion of maximally different, equally strong models. the lab race is breeding exactly that lineup
labs deliberately keep reasoning verbose. the same labs set the research agenda. that leaves an enormous field untouched
only the boldest ideas are worth a human's time now. the incremental rest, agents will grind out anyway
career
2026
Stealth RL Lab ($10M funded)cto
lead a team of 5, own the RL pipelines: data, training, evals. researching cross-model reasoning in latent space
2025
Fluently (YC W24)founding engineer
owned the core AI: built the real-time voice agent from scratch (sub-500ms), replaced vendor APIs with in-house RL-post-trained LLMs, shipped to millions. 0 → $8M+ ARR in nine months
2021–2025
Neiro.aidl engineer → head of product
novel speech research, trained in-house LLMs (TTS + text), shipped to 100k+ users, ran a 15-person team, took the product 0 → $150k+ net MRR
2019–2021
JetBrains Researchdl researcher · team lead
led the deep learning research team: papers, mentoring, built a tool for reading scientific papers
M.Sc. in ML
B.Sc. in math
papers
Max Out GRPO Signal: Adaptive Trace Prefix Control for Hard Reasoning Problems
the hardest problems become the strongest RL signal · arxiv
Agon: Competitive Cross-Model RL with Implicit Rival Grading of Reasoning
two models grade each other's reasoning, a step toward latents · arxiv
SpeechNet: Weakly Supervised, End-to-End Speech Recognition at Industrial Scale
trained without human labels, shipped at 12M queries a day · arxiv
End-to-end Deep Object Tracking with Circular Loss Function for Rotated Bounding Box
transformer tracker with a custom loss, beat SoTA on VOT Challenge · arxiv
Transformer-Based Open Domain Biomedical Question Answering at BioASQ8 Challenge
open-domain QA with BERT, before LLMs made it easy · arxiv