Back
Tier-1 brand, metro location, and mid-level experience increase applicant density despite niche MLIR/GPU specialization.
Niche MLIR and GPU compiler expertise yields high domain specificity, so background fit sensitivity is high.
Explicit degrees, years, and many mandatory MLIR/GPU/C++ requirements make shortlisting highly strict.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Design, optimize, and deploy high-performance GPU compute kernels targeting OpenCL and Vulkan for AI/ML workloads.
Build and extend MLIR compiler backends and dialects at various abstraction levels to enable efficient model compilation and runtime performance.
Conduct GPU kernel profiling and implement compiler-level optimizations; maintain GPU runtime infrastructure and collaborate with teams to optimize model lowering for CV and LLM workloads.
Bachelor's degree in Engineering, Information Systems, Computer Science or related with 4+ years experience, OR Master's with 3+ years, OR PhD with 2+ years in Systems Engineering or related.
Strong hands-on experience with MLIR framework including custom dialects, compiler passes, and lowering pipelines.
Proficient in OpenCL programming and Vulkan compute programming with deep understanding of GPU architecture and memory hierarchies.
Proficiency in C/C++ for system-level development and experience in GPU kernel profiling and bottleneck analysis.
Expertise in MLIR across multiple abstraction levels including frontend, graph-level IR, tensor IR, and runtime/low-level dialects for end-to-end GPU compilation.
Experience designing performance-critical schedules (tiling, fusion, parallelism) and extensive use of profiling tools for GPU compute optimization.
Strong background in machine learning fundamentals covering both computer vision (CV) and large language model (LLM) workloads in high-throughput AI environments.