Top Tech Jobs & Startup Jobs in Toronto

Develop and extend Intel's LLVM-based compilers (C, C++, SYCL, Fortran) to support new language standards, implement compiler features, optimization passes and code generation, collaborate upstream with the clang/LLVM community, debug complex compiler issues, and contribute to oneAPI toolchain efforts.

Lead the design, development, optimization, testing, and maintenance of compiler technologies for Triton, DSLs, and AI programming models. Own compiler stack components spanning front-end, optimization, code generation, runtime integration, and tooling. Collaborate across hardware and AI software teams, resolve complex performance and correctness issues, contribute to LLVM, MLIR, and Triton open-source projects, shape technical roadmaps, and mentor engineers.

Design, implement, test, debug, and optimize compiler features for Triton, domain-specific languages, and AI programming models. Develop compiler analyses, transformations, and code-generation technologies using LLVM and MLIR. Collaborate with hardware architects and AI framework developers, contribute to open-source compiler projects, and improve performance across heterogeneous computing platforms.

Develop and maintain LLVM-based compiler technologies for Intel CPUs, GPUs, and accelerators. Responsibilities include implementing compiler features, debugging defects, optimizing generated code, analyzing workloads and benchmarks, conducting functional and performance testing, enabling processor capabilities, and contributing to open-source initiatives. The role collaborates with hardware architects and global engineering teams across AI, HPC, and other demanding workloads.

Develop and advance LLVM-based compiler technologies for Intel CPUs, GPUs, and accelerators. Design, implement, test, debug, and maintain compiler features; optimize generated code; analyze workloads and benchmarks; enable processor capabilities; and conduct functional, performance, scalability, and stress testing. Collaborate with hardware and global engineering teams, contribute to open-source initiatives, and provide technical leadership and mentorship.

Develop and optimize emulation and FPGA models for presilicon verification, postsilicon validation, and software development. Build models using synthesis, partitioning, and routing tools; debug hardware-software integration issues; create automation scripts and emulation methodologies; improve RTL development acceleration; support SoC and IP bring-up; and collaborate with design, silicon validation, and software teams.

Leads a team developing Triton compiler technologies for Intel GPUs and AI accelerators. Responsibilities include compiler design and optimization, project delivery, cross-functional collaboration, software quality, performance analysis, open-source contributions, hiring, mentoring, and career development. The role requires technical leadership in compiler technologies, AI/ML workloads, GPU architectures, and software engineering practices.

Develop and maintain Triton compiler front-end and back-end components for Intel GPUs. Design and implement optimization passes, code generation, testing, debugging, and releases. Collaborate with hardware teams, compiler partners, and programming communities; participate in language/standards groups.