AI Technical Writer

Senior Technical WriterLocation: Farmington Hills, MI Contract: 5+ Months (Long Term Contract) Working Mode: HybridExperience: 5 - 7 years Must Have:3-4 years of Document Control experienceAuthorTaxonomy DevelopmentTechnical ManualsVocabularySummary: We are looking for a Senior Technical Writer to join our AI agentic engineering team.You will develop and manage the knowledge catalog that our production AI agents read from — authoring the entries that encode how our IT enterprise actually works, and structuring them so agents retrieve the right knowledge at the right moment.This is a writing role at its core, but the reader is different.Your audience is an AI agent operating under a context budget, and behind it, the engineer who has to trust what that agent produces.Success is measured less by page count than by whether agents behave correctly because your entries were clear, correctly scoped, and easy to find.What You'll Do:Author knowledge entries — service overviews, runbooks, decision records, schemas, specifications, and glossary terms — drawn from workflows, policies, engineering standards, and technical documentationWrite the short descriptions and summaries that drive progressive disclosure — the text an agent reads to decide whether loading the full entry is worth the context it costsStructure orientation paths so an agent onboarding to an unfamiliar domain encounters the mental model, entry points, and invariants first, and drills into detail only on demandMaintain hierarchy coherence across a growing catalog — cross-linking, indexing, reachability, and the layered structure that keeps entries discoverable as the corpus scalesOwn the scoping metadata that routes entries to the right consumer in the right context — precision here determines whether an agent gets the relevant standard or the wrong oneAuthor and maintain prompt assets — reusable skills, agent instructions, and reference material consumed directly by production agentsCodify engineering constitutions — turn review standards, security requirements, and platform conventions into structured, versioned rules that automated code review agents apply on every pull requestInterview developers and engineers to capture the rationale behind decisions — the "why" is rarely present in the source material, and it is usually the part that matters mostAdvance entries through review and approval with engineering and governance partners, so only verified content reaches production consumersGovern vocabulary — maintain the glossary and naming conventions, resolving terminology collisions before they propagate into schemas, tooling, and agent behaviorKeep the catalog current — identify and retire stale entries as the systems they describe changeCore Capabilities:Writes with precision under hard length constraints, where an unnecessary sentence carries a measurable costStructures information for machine consumption as fluently as for human readersReads primary source material — code, configuration, infrastructure definitions, runbooks — accurately enough to summarize it without an engineer rewriting the resultInterviews technical staff effectively and recognizes when an answer is incompleteSustains consistency of voice, terminology, and structure across a large, cross-linked corpusExercises editorial judgment about what belongs in the catalog, what should be merged, and what should be removedPartners credibly with developers, engineers, and governance teams without needing content pre-digestedWhat You Will Bring:5–7 years of technical writing experience in software, platform, or infrastructure environmentsDemonstrated ability to produce accurate technical content from primary sources — code, configuration, specifications, runbooks — with limited hand-holdingStrong information architecture instincts: taxonomy, cross-linking, layered structure, and progressive disclosureExperience authoring reference material, standards, or specification documentation consumed by engineersComfort working directly with developers and engineers, including the credibility to push back when source material is incomplete or contradictoryExperience partnering with governance, risk, security, or compliance stakeholdersEditorial discipline — consistency of terminology, voice, and structure maintained across many documents and contributorsFamiliarity with docs-as-code practice: Markdown, version control, and content that lives in a repository alongside the systems it describesClear verbal communication — much of the source material is gathered in conversation, not handed overNice to Have:Hands-on experience writing prompts, agent instructions, or reusable skill definitions for LLM-based systemsUnderstanding of context management techniques for AI agents — progressive disclosure, context window economics, retrieval strategyExperience with structured content — YAML or JSON frontmatter validated against a schema, content models, or typed document formatsWorking comfort with Git and CLI-based authoring workflows — pull requests, validation tooling, link checking, and CI feedbackExposure to taxonomy design, ontologies, knowledge graphs, or controlled vocabulariesBackground in developer documentation, API documentation, or internal platform documentationFamiliarity with AI agent concepts — tool use, orchestration, retrieval, and agent context protocols such as MCPReading-level familiarity with Python, TypeScript, Terraform, or YAML-based configurationExperience in banking, financial services, or another regulated industry