Software Engineer, Systems ML - Frameworks / Compilers / Kernels

Job Description

About the Role

In this role, you will be a member of the MTIA (Meta Training & Inference Accelerator) Software team and part of the industry-leading PyTorch AI framework organization. The MTIA Software Team has been developing a comprehensive AI Compiler strategy that delivers a highly flexible platform to train and serve new deep learning and machine learning model architectures, combined with auto-tuned high performance for production environments across specialized hardware architectures. You will work on core areas such as PyTorch framework components, AI compiler and runtime, high-performance kernels, and tooling to accelerate machine learning workloads on current and next-generation MTIA AI hardware platforms. The role involves analyzing deep learning models, developing compiler optimizations, and collaborating with hardware teams to enhance performance and deployment velocity at Meta.

Key Responsibilities

Development of software stack with a focus on AI frameworks, compiler stack, high-performance kernel development, and acceleration onto next-generation hardware architectures.
Contribute to the development of PyTorch AI framework core compilers to support new AI hardware accelerators and optimize their performance.
Analyze deep learning networks and develop and implement compiler optimization algorithms.
Collaborate with AI research scientists to accelerate the next generation of deep learning models such as Recommendation systems, Generative AI, Computer vision, NLP, etc.
Perform performance tuning and optimization of deep learning framework and software components.

Requirements

Proven C/C++ programming skills.
Currently has, or is in the process of obtaining, a Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience. Degree must be completed prior to joining Meta.
Experience in AI framework development or accelerating deep learning models on hardware architectures.
Knowledge of GPU, CPU, or AI hardware accelerator architectures.
Experience working with frameworks like PyTorch, Caffe2, TensorFlow, ONNX, TensorRT or AI high-performance kernels such as CUDA, OpenMP / OpenCL, or AI hardware accelerator kernel programming.
Experience in accelerating libraries on AI hardware such as cuBLAS, cuDNN, CUTLASS, HIP, ROCm, etc.
Experience with compiler optimizations such as loop optimizations, vectorization, parallelization, and hardware-specific optimizations like SIMD.
Experience with MLIR, LLVM, IREE, XLA, TVM, Halide is a plus.
Experience in developing training and inference framework components.
Experience in system performance optimizations including runtime analysis of latency, memory bandwidth, I/O access, compute utilization, and tooling development.

Nice to Have

Experience with MLIR, LLVM, IREE, XLA, TVM, Halide.

Qualifications

Bachelor's degree in Computer Science, Computer Engineering, or relevant technical field with 4+ years of experience, or a Master's degree with 2+ years of experience, or a PhD in a relevant field.

Apply Now