Reinforcement learning engineer with a graph processing bent
Engineers reinforcement learning frameworks and graph partitioning tooling. Commits to verl-project/verl, a post-training framework for reinforcement learning.
BearBiscuit (BearBiscuit05) is a software engineer who works mostly in python, c++ and java. Reinforcement learning engineer with a graph processing bent Vamo shows BearBiscuit on the Engineers who built Qwen Discover list for their work on QwenLM/Qwen3, read from what they have shipped on GitHub.
BearBiscuit and others on Engineers who built Qwen
Reinforcement learning engineer with a graph processing bent
Engineers reinforcement learning frameworks and graph partitioning tooling. Commits to verl-project/verl, a post-training framework for reinforcement learning.
Active 11 months ago
Engineers reinforcement learning frameworks and graph partitioning tooling. Commits to verl-project/verl, a post-training framework for reinforcement learning.
2 contributions this year
ML engineer building fine-tuning tooling for large language models
Builds fine-tuning libraries for large language models from Beijing. Creator of LlamaFactory, a library for fine-tuning language models, and maintains EasyR1, a framework for multi-modality reinforcement learning training.
Active 1 day ago
Builds fine-tuning libraries for large language models from Beijing. Creator of LlamaFactory, a library for fine-tuning language models, and maintains EasyR1, a framework for multi-modality reinforcement learning training.
4,931 contributions this year
TypeScript developer tools engineer for AI-generated UI workflows
Ships developer tools connecting AI design to code from Washington. Maintains stitch-mcp, a CLI for moving AI-generated UI designs into development workflows, and builds Querybase, a library for querying Firebase databases.
Active 1 day ago
Ships developer tools connecting AI design to code from Washington. Maintains stitch-mcp, a CLI for moving AI-generated UI designs into development workflows, and builds Querybase, a library for querying Firebase databases.
20,431 contributions this year
Engineers reinforcement learning frameworks and graph partitioning tooling. Commits to verl-project/verl, a post-training framework for reinforcement learning.
27,663 stars GitHub
Contributors to the Qwen model, agent and coding repos, ranked by devRank.
Find engineers like BearBiscuit in Vamo, see BearBiscuit05 on GitHub, or browse every developer on Vamo's public lists.
Is this you? Email support@vamo.app and we will edit or take down this page.
© 2026 Vamo Holdings, Inc.