10 часов назад
Technical Writer (AI)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Technical Writer (AI) (Furiosa SDK/Furiosa-LLM): Creating developer documentation, API references, tutorials, and release guidance for AI software stacks with an accent on precise explanations of compilers, runtimes, and inference workflows. Focus on building docs-as-code pipelines, validating code samples against real RNGD hardware, and keeping versioned documentation aligned with rapidly changing APIs.
Location: On-site at the Seoul HQ, Seoul, South Korea
Company
develops AI software and hardware, including the Furiosa SDK, Furiosa-LLM, and RNGD accelerator hardware.
What you will do
- Write developer-facing documentation for the Furiosa SDK and Furiosa-LLM, including API references, conceptual guides, tutorials, quickstarts, migration guides, and release notes.
- Build and operate the MDX-based docs-as-code toolchain, including automated API-reference generation, link checks, and sample validation in CI.
- Design hardware-in-the-loop validation pipelines that compile and run documentation samples and end-to-end inference examples on RNGD hardware.
- Partner with engineers to capture technical details and keep documentation aligned with releases, deprecations, and breaking changes.
- Define documentation standards for style, terminology, information architecture, and versioning.
Requirements
- Bachelor's degree in Computer Science or equivalent experience.
- 3+ years of technical documentation experience for developer-facing software such as SDKs, APIs, systems software, or ML frameworks.
- Strong written English and the ability to explain low-level systems concepts precisely.
- Working proficiency in Python and command-line tooling, with the ability to read source code, run build and inference workflows, and validate code samples.
- Experience with Git-based docs-as-code workflows, Markdown/MDX, and documentation checks in CI.
- Understanding of DNNs and LLMs, including how models are built, run, and served.
Nice to have
- Experience documenting ML inference frameworks, compilers, runtimes, or accelerator/GPU software stacks.
- Knowledge of LLM inference concepts such as serving, batching, quantization, KV cache, and distributed inference.
- Familiarity with PyTorch, Hugging Face, CUDA, or Triton.
- Experience with documentation platforms such as Fumadocs, Mintlify, or Sphinx and automated API-reference pipelines.
- Fluency in Python and Rust sufficient to read, write, and validate code samples.
Culture & Benefits
- Full-time, on-site work at the Seoul headquarters.
- Cross-team collaboration with engineers working on compilers, runtimes, SDKs, LLM inference, and accelerator hardware.
- Documentation is treated as a versioned and continuously tested software artifact.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →