Compiler Engineer for AI Tile-based DSL

Job Title

Compiler Engineer for AI Tile-based DSL

Role Summary

You will design, develop, test, and optimize compiler middle-end and backend technologies for Intel architectures, focusing on LLVM- and TileIR-based domain-specific compilers for tile-based AI programming models.

The role sits on the Compiler Technology Innovation team in Intel's Data Center Group and collaborates with hardware engineers and open-source communities to enable AI workloads on Intel CPUs, GPUs, and accelerators.

Experience Level

Entry-level - 1+ year of relevant experience in compiler development or related compiler technologies.

Responsibilities

Primary responsibilities include:

• Design, implement, test, and optimize compiler middle-end and backend features for Intel CPU and GPU architectures.
• Develop and maintain LLVM- and TileIR-based compiler components and DSL support (TileLang, cuTile).
• Implement optimizations for parallelization, vectorization, and target-specific code generation.
• Integrate compiler support for new processor features through collaboration with hardware teams.
• Develop and maintain tooling and front-end integrations such as Clang, DPC++, and SYCL where relevant.
• Create and run comprehensive test cases to validate functionality and performance.
• Diagnose and fix software bugs using debugging and performance analysis techniques.
• Collaborate with internal teams and upstream open-source projects (Clang/LLVM) and participate in technical discussions with external partners.

Requirements

Must-have and nice-to-have skills:

• Must-have: Proficiency in C/C++ and object-oriented design; experience with complex data structures.
• Must-have: Working knowledge of compiler technologies and the LLVM infrastructure; hands-on experience with middle-end or backend compiler development.
• Must-have: Experience writing tests and using debugging and performance-analysis tools to verify compiler functionality.
• Must-have: Ability to collaborate with hardware teams and open-source communities.
• Nice-to-have: Experience with Clang, MLIR, DPC++, SYCL, CUDA, or GPU programming models.
• Nice-to-have: Experience with vectorization, AVX, OpenMP, TileLang, cuTile, or production-grade compiler development.
• Nice-to-have: Familiarity with performance optimization and advanced debugging techniques.

Education Requirements

Bachelor's degree in Computer Science, Applied Mathematics, Electronic Engineering, Informatics, or a closely related technical discipline.

About the Company

Company: Intel Corporation

Headquarters: Santa Clara, California, USA

Intel Corporation is a leading multinational technology company known for its innovative semiconductor solutions, including microprocessors, artificial intelligence accelerators, and memory products. Headquartered in the United States, Intel focuses on cutting-edge technology and a collaborative working environment, driving advancements in semiconductor manufacturing to meet global demands. The company emphasizes professional development and aims to shape the future of technology through groundbreaking designs.