Documentation Engineer

Location: Poland | Work model: remote

DataWalk is the Data and Analytics Platform with an Enterprise Knowledge Graph. DataWalk turns fragmented data into an enterprise knowledge graph - enabling humans and AI to uncover hidden patterns and answer complex multi-hop questions at a population scale. Our system is used by US Departments, Intelligence Agencies, and top Fortune500 companies to combat money laundering, fraud, human trafficking, terrorism, or organized crime. If you are interested in making the world a safer place and leveraging a unique business opportunity, please read further.

We are looking for an experienced Documentation Engineer to join our Product Engineering Team.

Documentation Engineer will own and scale the next generation of product and technical documentation by designing, building, and orchestrating AI-driven documentation systems. Rather than manually writing every document from scratch, the Documentation Engineer designs multi-agent workflows, LLM orchestration pipelines, and tooling (MCPs, CI/CD bots, ticket/repo analyzers) that ingest product specifications, Jira refinements, codebase changes, and QA test cases to continuously draft, audit, cross-link, and maintain accurate, high-quality documentation across the DataWalk ecosystem.

The scope spans both pillars of DataWalk documentation:
1. Analytical & Conceptual Product Features: Translating complex graph algorithms, analytical patterns (pathfinding, graph traversals, clustering, link analysis, visual investigative workflows), dashboards, and charts into clear, user-centric guides.
2. Technical & Developer Artifacts: System configuration keys, feature flags, REST APIs, SDKs, and release notes synchronized directly from code and release branches.

Responsibilities:

AI-Orchestrated Documentation Workflows: Design, implement, and maintain automated AI pipelines and subagents using Claude Code, OpenCode, Gemini Enterprise and/or n8n (agent harnesses, custom MCP servers, scripts) that track codebase changes, Jira tickets/refinements, and product specs to automatically draft, update, and audit documentation.
Analytical & Conceptual Knowledge Synthesis: Build agent workflows that distill complex data analytics concepts—such as graph traversal, shortest path algorithms, clustering methods, geospatial analysis, and investigative workflows—into intuitive, structured explanations, user scenarios, and step-by-step guides.
Documentation Architecture & Platform Management: Manage and optimize the documentation portal (DokuWiki, Markdown/Docs-as-code structures), ensuring clean information architecture, namespace taxonomy, templating, and searchability.
Quality Assurance & Verification Loops: Establish automated checks, linting, dead-link auditing, and human-in-the-loop evaluation frameworks to ensure all AI-generated technical content is accurate, consistent with house style, and properly referenced.
Release Synchronization & Feature Coverage: Ingest technical release artifacts, system configurations, feature flags, REST APIs, and SDK updates to produce timely release notes, feature guides, and reference manuals.
Agent Skills & Prompt Tooling: Build and refine agent skills, subagents, prompt workflows, and Model Context Protocol (MCP) servers tailored for Claude Code and OpenCode, empowering engineering, product, and QA teams to contribute seamlessly to documentation.
Editorial & Analytical Stewardship: Review, polish, and validate critical customer- and analyst-facing documentation to ensure clarity, correctness, and pedagogical quality.

Requirements:

Software Engineering / Scripting Proficiency: Strong hands-on coding ability in Python and/or TypeScript / JavaScript, with comfort using Git, CLI tools, Linux environments, and REST/RPC APIs.
Hands-on Mastery of Target AI Stack: Deep practical experience orchestrating and working with agentic coding environments and LLMs—specifically Claude Code, OpenCode, and Gemini Enterprise / Google Vertex/Workspace AI ecosystem, along with Model Context Protocol (MCP) integrations.
Ability to design and follow user workflows to effectively guide LLMs in explaining complex analytical concepts to end users.
Code & Specification Literacy: Ability to read and understand backend/engine code (Java, Python), architectural diagrams, Jira refinements, and QA test suites to extract both functional business logic and technical contracts.
Developer Mindset on Documentation: Strong belief in "Docs-as-Code", structured templating, programmatic link auditing, and automating repetitive tasks rather than doing manual copywriting.
Communication & Clarity: Exceptional written and spoken Polish and English with the ability to structure complex technical and analytical concepts logically, concisely, and clearly.
CI/CD & Automation Integration: Experience integrating automated scripts/hooks into CI/CD pipelines (GitLab CI, GitHub Actions) or webhook-driven automation scripts.

Nice to have:

Data & Graph Analytics Literacy: Strong conceptual grasp of data analytics, graph databases/networks (nodes, edges, traversals, pathfinding, clustering, aggregations).
Experience with wiki platforms (DokuWiki) and modern docs-as-code frameworks (MkDocs, Docusaurus, VitePress, Sphinx).
Experience authoring custom OpenCode / Claude Code skills and subagents.
Background in Developer Relations (DevRel), Developer Experience (DevEx), or platform engineering.
Experience with semantic search, embeddings, vector indexing, or knowledge graphs.
Understanding of enterprise analytics, graph databases, or distributed systems concepts.

Technical tools and stack:

Primary AI Stack: Claude Code, OpenCode, Gemini Enterprise (APIs & workspace tooling), Model Context Protocol (MCP servers & tools).
Languages & Scripting: Python, TypeScript / JavaScript, Bash / Shell scripting.
Workflow & Automation: GitLab CI/CD, GitHub Actions, custom CLI tools / agent scripts, REST APIs, n8n.
Documentation & Knowledge Base: DokuWiki, Markdown, JSON/YAML schemas.
Development & Issue Tracking: GitLab, Jira Cloud (JQL, Jira REST API / automation), Git.

We offer:

Direct impact on the global expansion of the fast growing investigative analytics company with global ambitions.
A competitive compensation and access to professional development tools.
Growth opportunities in a dedicated and passionate team of professionals.
A challenging and inspiring environment.
Work remotely in a flexible, independent work environment.

If you are interested, please send your CV or Linkedin Profile to: praca@datawalk.com

Please include the following statement in your application: “I agree that my personal data will be processed by DataWalk S.A. in order to recruit for the position I am applying for.”

Before sending your application please read how we process your personal data:

Information on processing of personal data