About the Job

Owns the developer-facing documentation that makes FuriosaAI's software stack — the Furiosa SDK and Furiosa-LLM — usable, from API references and conceptual guides to tutorials, quickstarts, and release notes. This is a docs-as-code role: reading source, running the stack on real hardware, and producing precise, verifiable documentation that keeps pace with a fast-moving compiler, runtime, and inference codebase — backed by automated pipelines that continuously validate that documentation against the live codebase and hardware.

Responsibilities

• Owns and writes developer documentation for the Furiosa SDK and Furiosa-LLM — API references, conceptual guides, tutorials, quickstarts, and migration guides — translating complex systems behavior into clear, accurate, task-oriented content.

• Builds, maintains, and operates the documentation toolchain and docs-as-code pipeline (MDX-based static sites, automated API-reference generation, automated link and sample validation in CI), treating documentation as a versioned, testable artifact that is continuously verified against each SDK release.

• Designs and runs automated, hardware-in-the-loop validation pipelines that continuously authors and verifies runnable code samples and end-to-end examples against real RNGD hardware and released packages, catching drift early and ensuring every snippet compiles, runs, and reflects current APIs.

• Partners with engineers across diverse teams to capture design intent and surface accurate technical detail, then drives documentation to keep up with release cycles, deprecations, and breaking changes.

• Defines and enforces documentation standards — style, terminology, information architecture, and versioning — so content stays consistent and discoverable across the SDK and Furiosa-LLM.

• Produces release notes, changelogs, and upgrade and migration guidance that clearly communicate what changed across SDK and Furiosa-LLM versions.

Minimum Qualifications

• Bachelor's degree in Computer Science or equivalent work experience, with 3+ years writing technical documentation for developer-facing software (SDKs, APIs, systems software, or ML frameworks).

• Strong written English with the ability to explain low-level, systems-level concepts precisely and concisely.

• Working proficiency in Python and command-line tooling; comfortable reading source code, running build and inference workflows, and writing and validating code samples.

• Fluency with Git-based docs-as-code workflows and Markdown/MDX, including running documentation checks in CI.

• Solid understanding of deep neural networks (DNNs) and large language models (LLMs) — how they are built, run, and served — sufficient to document inference workflows accurately.

• Strong communication skills for cross-team requirement gathering and technical alignment.

Preferred Qualifications

• Experience documenting ML inference frameworks, compilers, runtimes, or accelerator/GPU software stacks.

• Familiarity with LLM inference concepts (serving, batching, quantization, KV cache, distributed inference) and the PyTorch / Hugging Face ecosystem.

• Familiarity with GPU Kernel programmings (e.g., CUDA, Triton)

• Experience building and operating documentation platforms (e.g., MDX-based static site generators, Fumadocs, Mintlify, Sphinx) and automated API-reference pipelines.

• Experience designing information architecture and versioned documentation for software with frequent releases.

• Fluency in Python and Rust programming, sufficient to read, write, and validate code samples across the stack.