Senior AI Kernel & Performance Engineer | Equity

Meta; Menlo Park (CA); On-site; USD 154,000 - 217,000; Full time

Job summary

Meta in Menlo Park is seeking a Senior Software Engineer to own kernel and performance optimization for MTIA accelerators. You will design, implement, and tune high‑performance kernels across MTIA workloads, from the innermost loop to production pipelines.

You will work with C++, Python, and modern toolchains, profile across the stack, and collaborate with silicon teams on co‑design and pre‑silicon validation to maximize performance and efficiency.

Qualifications

• Strong programming experience in multi-threaded C++ and Python.
• Proven kernel optimization for GPUs/ASICs or SIMD vectors.
• Solid understanding of computer architecture and memory hierarchies.
• Ability to measure performance with rooflines and explain gaps.

Responsibilities

• Design and optimize high-performance compute kernels for MTIA accelerators.
• Profile and diagnose performance across the stack from kernel to hardware.
• Develop kernel authoring frameworks and libraries for others to use.
• Collaborate with silicon teams on hardware/software co-design and bring up.

Skills

C++

Python

Kernels optimization

Performance analysis

GPU/ASIC architectures

Roofline modeling

Tools

CUTLASS

Triton

CuTe

LLVM

MLIR

XLA

PyTorch

Job description

Meta in Menlo Park is seeking a Senior Software Engineer to own kernel and performance optimization for MTIA accelerators. You will design, implement, and tune high‑performance kernels across MTIA workloads, from the innermost loop to production pipelines.

You will work with C++, Python, and modern toolchains, profile across the stack, and collaborate with silicon teams on co‑design and pre‑silicon validation to maximize performance and efficiency.