AI Software Development Engineer (Compiler)

TL;DR

AI Software Development Engineer (Compiler): Researching and developing graph-based compilation algorithms for AI hardware accelerators with an accent on OpenVINO and MLIR infrastructure. Focus on optimizing neural network performance, designing scalable compilation flows, and implementing high-performance compilation passes.

Location: Must be based in or able to work on-site in Timisoara, Romania (Hybrid model)

Company

hirify.global is a global leader in computing innovation, driving the future of AI through advanced hardware accelerators, foundational software stacks, and specialized IP for client and data center segments.

What you will do

• Drive the design of compilation flows for future neural network architectures.
• Implement and optimize compilation passes for neural network workloads.
• Develop performance analysis, visualization, and profiling tools.
• Integrate and test changes, ensuring end-to-end task execution.
• Contribute to the compilation features roadmap planning.

Requirements

• BS/MS in Computer Science or a similar field.
• At least 3-4 years of professional programming experience.
• Excellent C++ programming skills.
• Strong background in production software engineering, including CI, code reviews, and testing.
• Proven experience working with large-scale, multi-component software systems.

Nice to have

• Experience with compiler technologies, LLVM, or MLIR.
• Background in graph-based algorithms (e.g., graph coloring, max-cut).
• Knowledge of AI hardware accelerators, GPU, or heterogeneous architectures.
• Experience with deep-learning frameworks and neural network mapping.
• Proficiency in Python.

Culture & Benefits

• Hybrid work model allowing flexibility between on-site and off-site work.
• Opportunity to work on state-of-the-art AI hardware and software stacks.
• Collaborative environment working with research, infrastructure, and software teams.
• Exposure to cutting-edge neural network optimization and compiler research.