Meta
Engineering Manager, ML Compilers (Triton / Kernel DSLs)
$219K–$301K
Bellevue, WA +1 · Manager · Full-time · Posted Sep 18, 2026
- Location
- Bellevue, WA
Menlo Park, CA - Experience
- 5+ years managing a software team; other experience requirements are stated without a duration.
About the job
Leads development of Meta’s ML compiler stack and kernel DSLs for MTIA accelerators, from compiler and kernel enablement to production deployment and hardware roadmap input.
What you'll do
- Lead development of the DSL compiler toolchain, including ML compiler integration, kernel enablement, collectives, and low-level DSLs.
- Manage teams delivering compiler infrastructure, kernel libraries, and production deployment across accelerator generations.
- Shape technical strategy and cross-functional roadmaps, contribute hands-on using AI tools, and mentor engineers.
What they ask for
- 5+ years managing a software team.
- Experience with compiler architecture and development, particularly ML compilers or DSLs.
- Experience executing full product life cycles and working with hardware architectures, including influencing architecture roadmaps.
- Experience with kernel-level performance optimization for AI accelerators.
Nice to have
- Experience with Triton, MLIR, or LLVM; PyTorch compiler internals such as Inductor; and GPU CUDA, OpenCL, or OpenMP programming.
- Open-source engagement and upstream contributions; AI workflow integration and responsible AI practices.
Pay
$219,000/year to $301,000/year (base salary)
Tools
Triton, MLIR, LLVM, PyTorch, Inductor, CUDA, OpenCL, OpenMP
AI focus
Develops compiler and kernel software for AI accelerators and uses AI tools to evaluate technical direction and improve workflows. The posting also asks for ongoing AI skill development and responsible AI practices.
Model-written summary · the original posting is authoritative