Deep Learning Compiler Engineer (MLIR/LLVM)

TL;DR

Deep Learning Compiler Engineer (MLIR/LLVM): Developing an MLIR-based compiler to drive performance improvements on hirify.global deep learning accelerators with an accent on designing and implementing new optimizations within MLIR and LLVM for deep learning applications. Focus on collaborating with architecture and performance teams to address compiler pipeline bottlenecks, and exploring novel compilation techniques to improve hardware utilization and efficiency.

Location: Hybrid role, based in Tel Aviv, Israel, with an expected future change to the Petah Tikva campus, Israel.

Company

hirify.global is a corporation that drives customer value by enabling differentiated experiences through leadership AI technologies and foundational software stacks, products, and services across various market segments.

What you will do

• Design and implement new optimizations within the MLIR and LLVM frameworks for deep learning applications.
• Collaborate with architecture and performance teams to identify and address bottlenecks in the compiler pipeline.
• Engage with internal customers and developers to understand requirements and support model-level performance tuning.
• Explore and prototype novel compilation techniques to improve hardware utilization and efficiency.

Requirements

• 5+ years of experience in C++.
• Background in high-performance computing or parallel programming.
• Strong analytical and problem-solving skills.
• Experience with development on Linux.

Nice to have

• Strong experience with compiler design and middle-end optimizations, preferably using MLIR and LLVM.
• Experience with code generation, performance analysis, and tuning for hardware accelerators.
• Knowledge of dataflow graphs, IR transformation, and optimization techniques.

Culture & Benefits

• Eligible for a hybrid work model.
• Work with a team focused on enabling differentiated experiences through leadership AI technologies.