Developer Advocate, MAX Inference & Serving

What you will do:

• 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.

What success looks like after 6 months