Software Engineer, GenAI Frameworks - MTIA

What you'll do

• Lead technical direction and end-to-end delivery for an inference framework area, including design, testing, rollout, and production hardening.
• Build and optimize serving, distributed inference, graph execution, compilation, and PyTorch integration for production workloads.
• Profile performance and validate accuracy across framework, runtime, compiler, kernel, and hardware layers; partner with engineering teams on hardware/software co-design.

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.
• Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience.

Nice to have

• Experience with AI accelerator platforms and bringing up a new hardware backend in a major machine learning framework.
• Experience with distributed inference or training at scale, long-context inference, low-precision numerics, or PyTorch compilation.

Pay

$183,997/year to $257,000/year (base salary)

Tools

Python, C++, Rust, PyTorch, TorchDynamo, FX IR, Torch Inductor, Triton

AI focus

Optimize and productionize generative AI inference on MTIA, including frontier language, multimodal, and diffusion models; validate accuracy and performance, and integrate AI tools to improve workflows.