Summary from listing
DeepInfra is hiring a Software Engineer to design, develop, test, optimize, and operate production systems for serving open-source AI models. The role involves building inference solutions with Python, C++, CUDA, and NCCL; maintaining model-serving systems; improving performance; and taking ideas from concept to production. Candidates need a bachelor’s or master’s degree in a relevant field, at least three years of relevant experience, strong software fundamentals, Python and AI/ML framework experience, and familiarity with Transformers and Diffusers.
