Compiler Performance Engineer

About This Role

• The Compiler Engineering team in Intel's Data Center Group is looking for talented and passionate compiler engineers.
• At Intel, we are building the next generation of software technologies that unlock the potential of heterogeneous computing.
• Our compiler technologies help developers harness CPUs, GPUs, and accelerators through high-performance, portable software.
• Our mission is to build, innovate, and deliver industry leading compilers and tools that maximize hardware performance for our customers and Intel silicon - advancing performance, scalability, reliability, and developer productivity for AI, HPC, and other demanding workloads, while supporting Intel's commitment to contributing to and collaborating with open-source communities.
• The team develops LLVM-based C, C++, SYCL, Triton, MLIR, Domain Specific Language (DSL), and Fortran compiler technologies for Intel CPUs and GPUs, working across the full compiler stack: language front ends, intermediate representations, optimization, code generation, debug information, runtimes, offload support, quality, and developer tooling.
• We offer great opportunity for technical development and career growth, including work on cutting-edge compiler technologies, coaching from senior engineers and leaders, and collaboration with talents around the world.
• Responsibilities In this position you'll join the software engineering team working on compiler performance and optimization.
• You will learn the magic behind a compiler - how source code becomes highly optimized machine code.
• You will: - Analyze performance issues in compiler-generated code and help root-cause them to specific optimization or code generation phases. - Tune workloads and measure performance on Intel CPUs and GPUs, and report regressions and optimization opportunities. - Design and implement test automation for continuous integration so performance and quality are tracked daily. - Help connect Intel hardware and compiler capabilities with AI and HPC software ecosystems such as PyTorch, inference engines, and machine-learning models. - Participate in upstream open-source work: filing issues, submitting patches, and following community review practice. - Implement and extend compiler components - optimization passes, code generation, runtime or offload support - under the guidance of senior engineers. - Grow into deep expertise in a chosen area - middle-end optimization, backend code generation, heterogeneous and offload compilation, or workload performance analysis.
• As a motivated software developer, you will collaborate with a multinational engineering team and have the opportunity to help redefine compiler technology and software tools.