Summary from listing
DeepInfra is hiring a Software Engineering Intern for its Sofia-based team to design, develop, test, and deploy inference solutions for large AI models. The intern will implement and optimize models using Python, C++, CUDA, and NCCL; monitor live services; contribute to feature development, bug fixing, and code reviews; and collaborate with engineering teams. The role requires a current bachelor's or master's degree in a relevant field, strong computer science fundamentals, Python and AI/ML framework experience, familiarity with Transformers and Diffusers, version control, and agile development skills.
