Founder engineering local model inference tooling
Works on local LLM inference tooling, after co-founding Caret.io. Contributes to ollama/ollama, an app for running local models, and to ggml-org/llama.cpp, a C/C++ library for LLM inference.
Emanuil Rusev (erusev) is a software engineer who works mostly in php, go and c++. Founder engineering local model inference tooling Vamo shows Emanuil Rusev on the Engineers who built llama.cpp Discover list for their work on ggml-org/llama.cpp, read from what they have shipped on GitHub.
Emanuil Rusev and others on Engineers who built llama.cpp
Founder engineering local model inference tooling
Works on local LLM inference tooling, after co-founding Caret.io. Contributes to ollama/ollama, an app for running local models, and to ggml-org/llama.cpp, a C/C++ library for LLM inference.
Active 1 day ago
Works on local LLM inference tooling, after co-founding Caret.io. Contributes to ollama/ollama, an app for running local models, and to ggml-org/llama.cpp, a C/C++ library for LLM inference.
6,718 contributions this year
CNCF maintainer building a self-hosted AI engine in Go
Builds self-hosted AI tooling that runs any model on any hardware without a GPU, after advisory work at Masa AI. Creator of LocalAI, an AI engine that runs models on any hardware, and maintains edgevpn, a decentralized peer-to-peer VPN.
Active 1 day ago
Builds self-hosted AI tooling that runs any model on any hardware without a GPU, after advisory work at Masa AI. Creator of LocalAI, an AI engine that runs models on any hardware, and maintains edgevpn, a decentralized peer-to-peer VPN.
14,359 contributions this year
C++ and Python engineer building local LLM tooling
Ships private local LLM tooling with vision and tool-calling support. Maintains textgen, a desktop app for local LLMs, and contributes to unslothai/unsloth, a local UI to run and train LLMs and diffusion models.
Active 1 day ago
Ships private local LLM tooling with vision and tool-calling support. Maintains textgen, a desktop app for local LLMs, and contributes to unslothai/unsloth, a local UI to run and train LLMs and diffusion models.
2,653 contributions this year
Works on local LLM inference tooling, after co-founding Caret.io. Contributes to ollama/ollama, an app for running local models, and to ggml-org/llama.cpp, a C/C++ library for LLM inference.
LLM inference in C/C++
c++ · 130,756 stars GitHub
Contributors to llama.cpp, ggml and whisper.cpp, the local inference stack that reached v1.0 in November 2026.
Find engineers like Emanuil Rusev in Vamo, see erusev 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.