AI Inference Software Engineer

Location: Toronto Office, hybrid

Company

hirify.global builds large-scale AI hardware and software systems designed to accelerate model training and inference.

What you will do

• Bring up open-source and proprietary ML models on hirify.global CSX systems.
• Translate model architectures, lower computational graphs, optimize compilers, integrate runtimes, and tune performance.
• Debug performance, numerical correctness, runtime integration, and hardware utilization issues.
• Propose and prototype improvements to tools, APIs, and automation flows for faster model bringup.

Requirements

• Bachelor’s, Master’s, or PhD in Computer Science, Engineering, or a related field.
• Experience working across Python modeling code, compiler IRs, performance profiling, and the broader AI toolchain.
• Strong debugging skills in performance, numerical accuracy, and runtime integration.
• Experience with deep learning frameworks such as PyTorch or TensorFlow and knowledge of model internals including attention, MoE, or diffusion.
• Proficiency in C/C++ and low-level optimization.
• Compiler development experience, particularly with LLVM or MLIR, and a strong background in optimization techniques involving NP-hard problems.

Culture & Benefits

• Competitive salary and benefits package.
• Professional growth and career advancement opportunities.
• Work on AI hardware, AI supercomputers, and model releases.
• Opportunities to publish and open-source AI research.
• Non-corporate work culture with an emphasis on learning, growth, and inclusion.