Machine Learning Framework/Runtime Software Engineer (C++)
Core
Develop, test, and improve software across the machine learning software stack, including runtimes, compilers, drivers, and hardware integration.
Role type
Machine Learning Framework/Runtime Software Engineer (C++)
Builds
Machine learning inference engines, runtime systems, and hardware-accelerated AI solutions for Arm technology.
Domain
Semiconductor / Machine Learning Infrastructure
Deliverable
production ML models (via careerplan.io/jobs/100703560400-machine-learning-frameworkruntime-software-engineer-c-at-arm)
Required skills
C++ software development, software engineering fundamentals, machine learning systems knowledge, hardware-accelerated AI, performance optimization, compiler technologies, GPU programming, model execution, benchmarking, testing, automated validation
Preferred skills
Experience with ML inference frameworks (LiteRT, TensorFlow Lite, ONNX Runtime), GPU compute technologies (Vulkan, OpenCL, TOSA), computational graphs, memory management, AOT/JIT compilation, CI/CD workflows
Technologies
C++, LiteRT, TensorFlow Lite, ONNX Runtime, Vulkan, OpenCL, TOSA, Arm technology
Responsibilities
Investigate functional and performance issues, contribute to solutions across runtimes, compilers, drivers, and hardware, develop and test software across the ML stack, optimize model execution and performance
Seniority
Individual Contributor (IC), entry to mid-level (open to interns and those with academic projects)
