Senior AI Runtime Engineer

Modular•United States / Canada,

1d•$216,000 - $324,000•Hybrid

About The Position

ML developers today face significant friction when deploying trained models. They work in a fragmented space with incomplete, patchwork solutions that require extensive performance tuning and model-specific optimizations. At Modular, we are building the next-generation AI platform that will radically improve how developers build and deploy AI models. A core part of this offering is a platform that enables customers to achieve state-of-the-art performance across model families and frameworks. As an AI Runtime Engineer, you will own a runtime that operates on various CPU and GPU hardware platforms, optimizing performance for diverse customer AI models.

Requirements

5+ years of experience working on high-performance computing systems.
Experience in C++ programming and complex software systems.
Experience with CPU or GPU runtime optimizations and performance analysis on CPUs, GPUs, or AI accelerators.
Proficiency with one or more profiling tools (CPU or GPU).
Creativity and curiosity for solving complex problems, a team-oriented attitude that enables you to work well with others, and alignment with our culture.

Nice To Haves

Experience with ML graph optimizations, parallel / distributed programming, heterogeneous ML computation, and/or code generation.
Exposure to MLIR, LLVM, and/or the Mojo programming language.
Advanced degree in Computer Science or a related area is a plus.

Responsibilities

Design and develop runtime and cross-stack optimizations to improve CPU and GPU efficiency, addressing issues such as CPU overhead, caching, and data locality across multiple devices.
Port the Modular runtime stack to new hardware platforms and develop an API to streamline this process.
Collaborate with the compiler, kernels, serving, and models teams to design core technologies that achieve state-of-the-art end-to-end performance on various CPU and GPU hardware.
Collaborate with the customer success team and engage with customers to understand their performance requirements and use cases.
Collaborate with tooling and infrastructure teams to design systems for automated performance analysis and benchmarking.