GPU Compute & MLIR Compiler Engineer — AI Workloads
Technology, Data & Digital · Software & Web Development · Software Engineering · Systems Engineering
In short
Qualcomm is seeking a skilled GPU compute, MLIR compiler, and kernel optimization engineer to work on AI workloads. This role involves designing and optimizing GPU kernels, extending MLIR compiler backends, and collaborating with ML, runtime, and hardware teams to enhance performance on modern GPU architectures.
Responsibilities
- Develop and optimize GPU compute kernels for OpenCL and Vulkan compute backends for AI/ML workloads.
- Design, build, and extend MLIR dialects across multiple abstraction levels for efficient model compilation.
- Implement and maintain MLIR-based compiler passes and transformations.
- Conduct profiling and bottleneck analysis of compiled kernels and drive performance improvements.
- Build and maintain GPU runtime infrastructure for OpenCL and Vulkan.
- Develop and extend code generation pipelines for automatic lowering to OpenCL and Vulkan GPU kernels.
- Implement performance-critical schedules within MLIR-based backends.
- Collaborate with framework teams to optimize end-to-end model lowering for computer vision and LLM workloads.
- Design and implement robust compiler and runtime components using modern C/C++.
Requirements
- Strong hands-on experience with MLIR framework, including authoring and extending custom dialects, writing compiler passes, and building end-to-end lowering pipelines.
- Deep expertise across MLIR abstraction levels: Frontend dialects (TOSA, StableHLO, ONNX-MLIR), Graph-level IR, Tensor IR (Linalg, Tensor, Vector), and Runtime/low-level dialects (bufferization, MemRef, SCF, GPU, LLVM).
- Strong hands-on experience in OpenCL programming, including kernel development, memory model, work-group/work-item optimization, and runtime management.
- Solid understanding of Vulkan compute programming, including descriptor management, compute pipelines, synchronization primitives, and runtime internals.
- Strong understanding of GPU architecture, memory hierarchies, and async compute.
- Proficiency in C/C++ for system-level development.
- Experience with kernel profiling and bottleneck analysis on GPU platforms.
- Strong background in machine learning fundamentals, covering both CV and LLM workloads.
Desired Qualifications
- Hands-on experience with IREE or other MLIR-based deployment frameworks such as TVM, XLA, or LLVM.
- Familiarity with IREE's compiler and runtime architecture, particularly its OpenCL and Vulkan HAL backends.
- Experience contributing to open-source MLIR or IREE projects.
- Knowledge of quantization, mixed-precision inference, and model optimization techniques for edge and server GPU targets.
- Exposure to multi-target compilation (CPU, GPU, NPU) using MLIR-based toolchains.
- Familiarity with cross-vendor GPU profiling tools for OpenCL and Vulkan workloads.
Benefits
- Qualcomm is an equal opportunity employer.
- Qualcomm is committed to providing an accessible process for individuals with disabilities.
- Qualcomm is committed to making our workplace accessible for individuals with disabilities.
Skills
MLIROpenCLVulkanC++LLVMTOSALinalgONNXTVMXLA
#GPU#AI#MLIR#compiler#optimization#kernel#OpenCL#Vulkan#compute#systems engineering
About Qualcomm
Enabling a world where everyone and everything can be intelligently connected.
Enabling a world where everyone and everything can be intelligently connected.\n\n
Company
QualcommJob Posted
2 weeks ago
Employment Type
Full Time
Work mode
On Site
Experience Level
Mid-Senior
Locations
Bangalore, India
Qualification
Bachelor, Master, Doctoral
Applicants
Be an early applicant
Similar Jobs
Sandvik
Tampere, FinlandTest Mine Development Engineer
Full Time Be an early applicant Posted 4 days ago
Microsoft
NetherlandsFiber Delivery Engineer
€78.8–133k/yr Full Time Be an early applicant Posted 4 days ago
Synopsys Inc
Stockholm, Sweden +1 moreApplications Engineer - EDA Verification
Full Time Be an early applicant Posted 4 days ago
Synopsys Inc
Stockholm, SwedenPrincipal Application Engineer - EDA Verification
Full Time Be an early applicant Posted 4 days ago
Emerson
Porsgrunn, NorwayField Sales Engineer
Full Time Be an early applicant Posted 4 days ago
Emerson
Lviv, UkraineSoftware Engineer
Full Time Be an early applicant Posted 4 days ago