Senior Software Engineer - AI Infrastructure & Simulators

Meta; Bellevue (WA); On-site; USD 180,000 - 240,000; Full time

Job summary

Meta is seeking an experienced software engineer to join the MTIA team to build simulators and other early software development platforms for pre-silicon AI accelerator work. You will own simulation models and contribute to scalable infrastructure.

Collaborate across hardware and software domains to evaluate data center performance, optimize inference and training workloads, and ensure reliable, high-performance accelerator designs.

Qualifications

• Bachelor's degree in Computer Science, Computer Engineering, or equivalent practical experience
• Master's or PhD in Computer Science, Computer Engineering, or related field
• 5+ years of experience in developing C++ codebase
• 5+ years experience in developing Python codebase
• Experience with performance benchmarking on distributed at-scale model training/inference; familiarity with SystemC, Qemu, Virtual Platform
• Demonstrated AI skill development and ability to integrate AI tools to optimize workflows
• Experience with responsible, ethical AI practices and bias mitigation
• Experience in AI/ML infrastructure/HPC domains with hardware accelerators/interconnects

Responsibilities

• Contribute to developer infrastructure, including simulation and HW emulation platforms for Meta's accelerator programs
• Support networking and compute hardware acceleration techniques to improve ML inference and training model performance
• Implement simulation models for Meta's Accelerator ASICs and evaluate data center performance
• Perform architectural analysis to ensure performance, scalability, and reliability
• Collaborate with architects and engineers to integrate simulation results into system design
• Define firmware for accelerators using instruction set simulators
• Collaborate with hardware teams to ensure accurate modeling of accelerator functionalities

Skills

C++

Python

SystemC

Qemu

Virtual Platform

AI tooling integration

Distributed training

NCCL

CUDA

Performance benchmarking

Education

Bachelor's degree

Master's or PhD

Tools

NCCL

PyTorch

CUDA

Job description

Meta is seeking an experienced software engineer to join the MTIA team to build simulators and other early software development platforms for pre-silicon AI accelerator work. You will own simulation models and contribute to scalable infrastructure.

Collaborate across hardware and software domains to evaluate data center performance, optimize inference and training workloads, and ensure reliable, high-performance accelerator designs.