Developer Advocate, MAX Inference & Serving

Modular•United States / Canada,

3d•$150,200 - $225,400•Hybrid

About The Position

Modular is building a next-generation AI infrastructure platform that unifies the many application frameworks and hardware backends, simplifying deployment for AI production teams and accelerating innovation for AI researchers and hardware developers. We are looking for a Developer Advocate to evangelize the MAX Platform's inference and serving capabilities with our user base and developer community. This involves creating technical content such as user guides and blog posts as well as giving talks at conferences, leading workshops, all with the goal of enabling our community of builders deploying models in production. Join our world-leading product team and be part of redefining how AI infrastructure is built and deployed.

Requirements

Demonstrable experience creating technical content for developer audiences. Send us a portfolio: blog posts, tutorials, videos, docs, or courses.
You understand the ML inference stack, including model serving architectures, GPU acceleration, and how MAX compares to vLLM, Triton Inference Server, and TensorRT-LLM.
Strong Python skills; systems programming experience (C++, Rust, or similar) is an advantage.
You learn new tools fast and produce accurate content quickly. A feature ships Tuesday, your tutorial goes out Thursday.
You can record, edit, and publish a technical video without a production team. Clear audio, good pacing, technically correct, not necessarily polished.
You write well. You explain complex ideas without losing precision, and you cut the filler.
You plan your own content calendar because you're in the community and know where developers get stuck.
A growth and leadership mindset, with a collaborative attitude that seeks to learn more from our customers, team members, and the broader market.

Nice To Haves

Experience programming GPUs using CUDA or ROCm.
Familiarity with the Mojo 🔥 programming language and MAX AI framework.
Familiarity with open source software development practices and communities.
Experience producing high-quality videos covering technical topics.

Responsibilities

Provide support and respond to questions from customers evaluating MAX for inference and serving, including some of the world's largest corporations.
Establish, run and publish benchmarks comparing MAX to serving frameworks like vLLM, Triton Inference Server, and TensorRT-LLM.
Foster an inclusive and welcoming environment for ML engineers and practitioners deploying models with MAX.
Collaborate with engineering and product teams to create tutorials, video guides, and examples demonstrating how the MAX Platform handles inference and serving workloads efficiently on both CPUs and GPUs.
Write blog posts and other educational content that inform prospective and current customers about MAX's inference and serving performance and functionality.
Engage with the community across GitHub, Discord, Twitter/X, and LinkedIn by facilitating discussions, answering questions, and providing support.
Act as a voice for the developer community internally, feeding inference and serving feedback back to engineering and product teams, shaping the future of the MAX Platform.
Represent Modular at conferences, summits, and industry events through presentations, panel discussions, and networking with industry professionals.
Contribute to Modular's broader developer relations, product, and marketing strategies.