Software Engineer, Systems ML - Compilers
Role Overview
Reality Labs develops VR, AR, and wearable AI devices; its silicon team works across computer vision, machine learning, graphics, sensors, firmware, and algorithms.
The engineer will help build a clean-slate compiler toolchain for deep-learning hardware used in AR/VR systems.
The work spans compiling PyTorch models into binaries for custom accelerator blocks and collaborating with compiler, ML, firmware, and ASIC specialists.
Key Skills for This Role
Full Job Posting
Role overview
Reality Labs develops VR, AR, and wearable AI devices; its silicon team works across computer vision, machine learning, graphics, sensors, firmware, and algorithms.
The engineer will help build a clean-slate compiler toolchain for deep-learning hardware used in AR/VR systems.
The work spans compiling PyTorch models into binaries for custom accelerator blocks and collaborating with compiler, ML, firmware, and ASIC specialists.
Responsibilities
- Lead architecture and implementation of ML compiler infrastructure, including IR, optimization passes, and code generation for custom accelerators.
- Design transformations for GPU, TPU, and edge accelerator constraints; develop LLVM/MLIR toolchains that compile PyTorch models to optimized custom-silicon binaries.
- Co-design compiler features with hardware architects for performance, power efficiency, and edge-device programmability.
- Improve toolchain efficiency, scalability, stability, and extensibility to new hardware targets.
- Lead technical roadmaps, coordinate teams, mentor engineers, review designs and code, evaluate performance, and resolve system issues.
- Coordinate with PyTorch, ExecuTorch, and other compiler teams to evaluate and incorporate innovations.
Minimum qualifications
- Bachelor's degree in Computer Science, Computer Engineering, a relevant technical field, or equivalent practical experience.
- 3+ years developing compilers, toolchains, or code optimization software.
- Experience with LLVM, MLIR, or similar compiler frameworks; designing intermediate representations and implementing optimization passes.
- Experience with GPU, TPU, or custom AI accelerator architectures.
- C++ experience for compiler and systems-level software development.
- Experience leading end-to-end technical design and delivery of compiler infrastructure across teams.
Preferred qualifications
- System-level development with PyTorch or TensorFlow and experience co-designing software and hardware with silicon architecture teams.
- Experience with ExecuTorch, TensorRT, XLA, or similar ML compilation and deployment frameworks.
- Ongoing AI skill development, responsible AI practices, or use of AI tools to improve workflows.
- Power and performance optimization for constrained edge devices or machine-code generation for edge inference.
Compensation
- Base salary is $183,997 to $257,000 per year, plus bonus, equity, and benefits.
- Individual compensation depends on skills, qualifications, experience, and location.
Apply for this job in 1 click
Skip the repetitive application forms
Install the Base Career Chrome Extension and autofill job applications across major job boards with your profile.
Trusted by over 500,000 job seekers on Base Career
More from this employer
More jobs at Meta
Program Manager, Product Data Operations, Family of Apps
, USA
Network Engineer, Foundation & Support (Edge/Backbone Infrastructure Design)
London, GBR
Privacy Security Engineer, Privacy & Data Protection - Applied AI
London, GBR
AI Systems Engineer, Hardware Architecture
, USA
Program Manager, Product Data Operations, Family of Apps
, USA
Security Engineer Lead, Security Foundations
, USA
Director Software Engineering - Central Security
, USA
Data Engineer, Product Analytics
London, GBR
Network Engineer, Foundation & Support (Edge/Backbone Infrastructure Design)
London, GBR
Senior Staff Machine Learning Engineer
London, GBR
Privacy Security Engineer, Privacy & Data Protection - Applied AI
London, GBR