Founding Engineer — Open-Source AI Deployment Tools
Core
Building developer tools and backend infrastructure to deploy, serve, monitor, and improve open-source AI models in real-world environments.
Role type
Founding Engineer (Open-Source AI Deployment)
Builds
Developer tools for model deployment, serving, monitoring, and improvement; backend systems and APIs for AI workflows.
Domain
Open-source AI, Model Serving, Infrastructure
Deliverable
production ML models | product features | infrastructure
Required skills
vLLM, TGI, Ollama, llama.cpp, TensorRT-LLM, Hugging Face, Meta Llama, Mistral, Qwen, DeepSeek, vector search, observability, dataset management, API design, backend system architecture, rapid prototyping
Preferred skills
Experience with open model ecosystems, familiarity with fine-tuning and evaluation workflows
Technologies
vLLM, TGI, Ollama, llama.cpp, TensorRT-LLM, Hugging Face, Meta Llama, Mistral, Qwen, DeepSeek
Responsibilities
Build developer tools for deploying and serving open-source AI models; Design workflows for fine-tuning, evaluation, and benchmarking; Integrate with open-source AI ecosystems for inference and observability; Build reliable backend systems and APIs; Contribute to early technical decisions and product direction.
Seniority
Founding, hands-on IC with strategic input
