Jiaming Ji
PhD Candidate
Peking University, Beijing, China
Summary
🤩
RockstarJiaming Ji is a PhD candidate at Peking University with four years of hands-on experience building safe and visually grounded reinforcement learning environments. Focused on Coding and LLM safety alignment through PKU-Alignment, he contributes as an ML engineer to OmniSafe—an influential SafeRL framework—where he enhanced environment rendering, added rgb_array support, and integrated vision inputs into observations. His work reflects a practical blend of research and engineering, improving visual interfaces for safety-critical RL tasks. Based in Beijing, he combines academic rigor with open-source impact, quietly specializing in the often-overlooked engineering details that make safe RL experiments reproducible and visually interpretable.
4 years of coding experience
Github Skills (9)
environmental10
deep-reinforcement-learning10
pytorch10
machine-learning10
dev-environment10
environ10
python10
reinforcement-learning10
enviroment10
Programming languages (4)
Github contributions (5)
PKU-Alignment/omnisafe
Nov 2022 - Mar 2023
OmniSafe is an infrastructural framework for accelerating SafeRL research.
Role in this project:
ML Engineer
ML EngineerContributions:6 releases, 341 reviews, 17 commits in 3 months
Contributions summary:Jiaming primarily contributed to the implementation and modification of environments related to the Safety-Gymnasium library within the OmniSafe framework. They added support for rendering with 'rgb_array' and added related metadata. The user also modified task environments, incorporating vision input into the observation space. These changes, along with the deletion of redundant render model, suggest a focus on improving the visual aspects and input mechanisms for reinforcement learning tasks.
pytorchbenchmark-suitedeep-learningreinforcement-learningsafe-reinforcement-learning
PKU-Alignment/Safe-Policy-Optimization
Jun 2022 - Sep 2022
NeurIPS 2023: Safe Policy Optimization: A benchmark repository for safe reinforcement learning algorithms
Contributions:9 reviews, 63 commits, 18 PRs in 3 months
reinforcement-learning-algorithmsrobustnessreinforcement-learningsafe-reinforcement-learninglearning-algorithms
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.