Experienced Machine Learning Framework/Runtime Software Engineer (C++)
Core
Design, develop, integrate, test, and optimise machine learning inference engines, runtime systems, and backend integration frameworks for AI model execution on Arm hardware.
Role type
Senior IC machine learning framework/runtime software engineer (C++)
Builds
ML inference engines, runtime systems, compiler flows, and hardware abstraction layers for Arm technology
Domain
Semiconductor / AI Acceleration / Machine Learning Systems
Deliverable
production ML models
Required skills
C++ development, ML inference framework experience (LiteRT, TensorFlow Lite, ONNX Runtime), graph processing, operator execution, memory management, backend integration, performance optimisation, hardware abstraction layer design
Preferred skills
GPU programming (Vulkan, OpenCL, TOSA), AOT/JIT compilation flows, operator partitioning and scheduling, model validation and benchmarking, CI/CD workflows, AI-assisted development tools
Technologies
C++, LiteRT, TensorFlow Lite, ONNX Runtime, Vulkan, OpenCL, TOSA, Arm NGP
Responsibilities
Analyse, investigate, diagnose, and resolve complex functional or performance issues across frameworks, runtimes, compilers, drivers, and hardware abstraction layers; Design and develop solutions within a large, modular codebase; Collaborate across runtime, compiler, driver, and hardware teams to optimise AI execution
Seniority
Senior, hands-on IC
