Description
Arm is hiring an ML Framework Integrations Engineer to develop and optimize C++, C, and Python software that connects machine-learning frameworks and LLM runtimes such as llama.cpp with Arm hardware acceleration. The role involves designing integrations, improving ML and LLM workload performance, leading work from design through delivery, mentoring junior engineers, and collaborating across Arm and technology-company teams. Required skills include strong C++, C, and Python programming, software design, Git and continuous-integration experience, technical leadership, and knowledge of LLM inference; experience with llama.cpp, workload profiling, compiler or ML-graph technologies, GPU compute APIs, and AI-assisted development tools is preferred.
