Software Engineer, LLVM Compiler - MTIA

What you'll do

• Set technical direction and deliver multi-quarter framework or infrastructure programs across teams, from design and testing through production rollout.
• Build and optimize GenAI inference, including serving frameworks, distributed inference, graph execution, compilation, and PyTorch integration.
• Improve production performance and quality by profiling across system layers, validating accuracy, and maintaining stability and test coverage.

What they ask for

• 8+ years of professional experience in systems software, ML infrastructure, performance engineering, or compiler/framework development.
• 5+ years of hands-on experience with generative AI inference or training frameworks, or production model-serving systems.
• Proficiency in Python, C++, or Rust, including low-level systems code and performance-critical paths.
• Experience with GenAI inference optimization, deep learning framework internals, runtime optimization, and leading cross-team technical delivery.

Nice to have

• Experience with AI accelerator platforms and bringing up a new hardware backend in a major machine learning framework.
• Familiarity with the PyTorch compilation stack, including TorchDynamo, FX IR, Torch Inductor, dynamic shapes, Triton, AOT I, and custom operator integration.

Pay

$183,997/year to $257,000/year USD base salary; bonus and equity amounts not stated

Tools

Python, C++, Rust, MTIA, PyTorch, TorchDynamo, Triton, AOT I

AI focus

Develop and optimize generative AI inference on MTIA, including model serving, distributed inference, and framework integration; the posting also mentions responsible AI practices and use of AI tools to improve workflows.