Jobs

Ollama is seeking a Software Engineer, Runtime to work on the core local runtime that enables open models to run efficiently on developers' machines. This role involves optimizing model loading, memory management, and GPU acceleration across diverse hardware using Go and C/C++. You will be responsible for making open models fast and reliable, integrating new architectures, and improving performance metrics like cold-start and throughput. The ideal candidate has strong systems fundamentals, experience with low-level programming, and a passion for performance optimization in an open-source environment.