Compiler Engineer, MTIA Software (Technical Leadership)

Job Title

Compiler Engineer, MTIA Software (Technical Leadership)

Role Summary

Principal-level compiler architect responsible for designing and implementing compiler infrastructure for MTIA (Meta Training and Inference Accelerator). The role covers the full compiler stack from high-level graph transformations and intermediate representations to low-level code generation and scheduling for custom AI accelerators.

Work includes performance optimization, hardware-software co-design with accelerator teams, and integrating compiler infrastructure with ML frameworks to enable production-quality code generation at scale.

Experience Level

Senior (principal-level). Years of experience not explicitly stated.

Responsibilities

Primary duties include:

• Design compiler architecture across the full MTIA compiler stack: graph compilers, intermediate representations, optimization passes, and code generation.
• Build extensible compiler frameworks and IRs that support rapid iteration and evolving ML model architectures.
• Identify and eliminate performance bottlenecks across the compiler stack, including graph-level optimizations, scheduling, and low-level code generation.
• Collaborate with MTIA hardware teams on hardware-software co-design and translate compiler analysis into accelerator architecture improvements.
• Develop and operationalize correctness, reliability, and performance validation practices for production code generation at scale.
• Integrate compiler infrastructure with ML frameworks such as PyTorch.
• Evaluate and adopt state-of-the-art compiler technologies (for example, MLIR) and incorporate best practices into the organization.
• Mentor engineers, lead compiler architecture reviews, and drive technical excellence in compiler development.

Requirements

Expectations are separated into must-have and nice-to-have items.

Must-have:

• Deep specialization in compiler development, code generation, or performance optimization for accelerators.
• Proven experience architecting production compiler infrastructure for ML accelerators, GPUs, or custom silicon.
• Hands-on experience with compiler intermediate representations, optimization passes, and code generation techniques.
• Experience developing high-performance systems software and a strong understanding of low-level optimization and hardware architecture.
• Track record of leading multi-year, cross-functional technical initiatives and influencing technical direction across teams.

Nice-to-have:

• Deep understanding of ML model architectures and their computational patterns.
• Familiarity with ML compiler stacks such as MLIR, XLA, TVM, or Glow.
• Experience with hardware-software co-design for custom ML accelerators or AI chips.
• Contributions to publications, open-source projects, or standards bodies related to compilers or ML systems.
• Experience defining and operationalizing performance benchmarks and correctness validation for compilers.
• Experience applying AI tools or automation to improve engineering workflows.
• Preferred advanced degrees (Master's or PhD) in relevant technical fields.

Education Requirements

Required: Bachelor's degree in Computer Science, Computer Engineering, or a related technical field, or equivalent practical experience. Preferred: Master's or PhD in Computer Science, Computer Engineering, or a related technical field. Equivalent practical experience is explicitly accepted where noted.

About the Company

Company: Meta Platforms

Headquarters: Menlo Park, California, United States

American technology company that develops social networking products (Facebook, Instagram, WhatsApp) and invests in virtual/augmented reality hardware and software through Reality Labs, focusing on connectivity, advertising, and immersive computing experiences.