Manajev AI Labs

Dmitri Manajev — Reinforcement Learning & Robotics engineer with 12+ years of engineering experience shipping production software. Multi-agent & continuous control (MAPPO, HAPPO, MADDPG, PPO, SAC, TD3) in PyTorch; Unity ML-Agents; ROS 2/C++; focus on reproducible training, evaluation, and deployment.

← Back to main site