Principal AI Compiler Engineer (AI)

TL;DR

Principal AI Compiler Engineer (AI): Architecting and scaling a production-class AI compiler toolchain for NXP SoCs with an accent on hardware-software co-design and AI-driven optimization. Focus on building graph transformations, codegen strategies, and deep integrations with frameworks like PyTorch and TensorFlow to maximize performance on custom accelerators.

Location: Must be based in Austin, TX, San Diego, CA, or San Jose, CA

Company

hirify.global is a global leader in secure connectivity solutions for embedded applications, driving innovation in automotive, industrial, and IoT markets.

What you will do

• Design and evolve an AI compiler toolchain that maps neural networks onto NXP SoC platforms.
• Develop graph transformations, scheduling, and codegen strategies for CPUs and custom accelerators.
• Integrate with AI frameworks including PyTorch, TensorFlow, and ONNX.
• Collaborate on hardware-software co-design to align silicon features with compiler capabilities.
• Optimize performance for latency, throughput, and power efficiency using AI-enabled profiling.
• Enhance validation and regression pipelines to ensure compiler correctness.

Requirements

• MS/PhD in Computer Science, EE, or equivalent experience.
• Deep experience building AI compilers, accelerator backends, or graph optimization frameworks.
• Strong expertise in performance optimization for NPUs or custom accelerators.
• Proficiency with MLIR, LLVM, TVM, or proprietary compiler IRs.
• Excellent C/C++ and Python programming skills.
• Solid understanding of AI inference workloads like CNNs and transformers.

Culture & Benefits

• Opportunity to work at the intersection of cutting-edge AI and hardware design.
• Collaborative environment working with visionary engineering teams.
• Focus on real-world impact through silicon and software co-design.
• Equal Opportunity Employer committed to diversity and reasonable accommodations.