Who is welcome here?

InferenceOps welcomes anyone who wants to understand how AI moves from a model to a dependable production service. Whether you are deploying your first open model, researching new serving techniques, or operating inference infrastructure at scale, there is a place for your questions, experience, and perspective.

Our community is for software and ML engineers, platform and infrastructure teams, SREs, researchers, architects, students, and independent builders. You might be exploring vLLM, llm-d, or Praxis; working with GPUs and Kubernetes; or tackling routing, observability, evaluation, latency, and cost. You do not need a particular job title, employer, technology stack, or level of experience to take part.

Participation can be as simple as reading a Field Note, asking a thoughtful question, attending a workshop, testing a blueprint, or sharing a lesson from your own work. Writing articles is one way to contribute, but so are reviewing an idea, suggesting a correction, and helping someone understand a difficult concept.

Community knowledge is publicly accessible, and contributions are editorially reviewed for clarity, technical substance, and usefulness. We welcome different viewpoints and encourage respectful discussion grounded in evidence, with room to learn, question assumptions, and improve together.

Learn. Connect. Contribute.

Questions and conversations

Use the feedback and discussion area on each Field Note to ask questions, share field experience, or suggest corrections. Meetups, workshops, technical talks, and working sessions provide opportunities to meet other practitioners.

Help shape shared knowledge

Contributors share useful technical knowledge. Stewards support editorial review, events, mentoring, the framework, and community operations. Recognition follows quality, usefulness, consistency, and community impact.

Come to learn. Stay to participate.