1 of 1 LLVM Jobs in Buckinghamshire

resolve performance bottlenecks across the stack, including model execution, scheduling, and hardware constraints. Collaborate with compiler engineers to improve code generation, execution paths, and memory layouts using tools like LLVM or MLIR. Work with hardware teams to ensure software fully leverages OTPU architecture capabilities. Extend ML frameworks (e.g., PyTorch, ONNX, OpenXLA) to support performance-critical inference paths. Lead design … of distributed systems, especially real-time or near real-time data processing. Strong programming skills in C++ and Python for performance-sensitive applications. Hands-on experience with ML compilers (LLVM, MLIR) and knowledge of runtime and scheduling optimizations. Practical knowledge of ML frameworks like PyTorch, ONNX, or OpenXLA, and how to optimize their execution. Experience scaling AI workloads across More ❯