Software Engineer, Systems ML - Frameworks / Compilers / Kernels

Meta is seeking a Software Engineer to join their MTIA (Meta Training & Inference Accelerator) Software team within the PyTorch AI framework organization. This role focuses on developing cutting-edge AI compiler technologies and optimizations for Meta's machine learning infrastructure. The position involves working on core areas including PyTorch framework components, AI compiler and runtime, and high-performance kernels to accelerate machine learning workloads on current and next-generation MTIA AI hardware platforms.

The role requires collaboration with AI researchers to analyze and optimize deep learning models for MTIA hardware, as well as partnership with hardware design teams to develop efficient compiler optimizations. The successful candidate will apply software development best practices to design features and performance tuning techniques, gaining valuable experience in developing machine learning compiler frameworks and contributing to next-generation hardware-software codesign for AI applications.

Key responsibilities include developing the software stack for AI frameworks, compiler development, and high-performance kernel optimization. The position offers the opportunity to work on industry-leading PyTorch AI framework core compilers and support new state-of-the-art inference and training AI hardware accelerators. The role involves analyzing deep learning networks, implementing compiler optimization algorithms, and collaborating with AI research scientists on various applications including Recommendation systems, Generative AI, Computer vision, and NLP.

The ideal candidate should have strong C/C++ programming skills and experience with AI framework development or hardware acceleration for deep learning models. Knowledge of GPU, CPU, or AI hardware accelerator architectures is preferred, along with experience in frameworks like PyTorch, TensorFlow, or ONNX. Additional valuable skills include CUDA programming, compiler optimizations, and system performance optimization experience.

Meta offers a competitive compensation package including base salary ranging from $70.67/hour to $208,000/year, plus bonus, equity, and comprehensive benefits. The position is based in Sunnyvale, CA, with additional locations available, and represents an opportunity to work at the forefront of AI infrastructure development at one of the world's leading technology companies.