Principal Automation Analyst

Job Requisition  # 26WD97787

Autodesk’s Technical Advisory organization is building a scalable knowledge platform that transforms implementation expertise from enterprise engagements into structured, reusable, and customer-facing guidance within Workflow Advisory.

The Principal Knowledge Acquisition Analyst is responsible for designing and operating the systems that capture and transform knowledge from consulting engagements. This includes building AI-powered extraction and transformation pipelines and ensuring raw implementation data is converted into structured, template-aligned outputs ready for downstream content production. Reporting to the Senior Manager, Content & Knowledge, you will operate at the intersection of consulting delivery, data, and AI systems.

You will own the upstream knowledge pipeline—from extracting implementation intelligence to delivering high-quality structured inputs aligned to the content model. In the first year, you will establish scalable AI-assisted capture and transformation pipelines and ensure knowledge is reliably converted into reusable, high-quality outputs.

• Design and operate AI-powered pipelines to capture knowledge from enterprise systems, meeting transcripts, and engagement artifacts
• Define and evolve the conceptual knowledge model, including key entities, relationships, and ontology governance required to organize and retrieve implementation knowledge at scale
• Manage and optimize AI agents, including prompt design, evaluation, and performance tuning
• Define content-type-specific chunking strategies for consulting artifacts and work with Engineering to implement retrieval-ready knowledge structures
• Define requirements and participate in embedding and vectorization evaluation to ensure captured knowledge can be effectively discovered through semantic search and AI-powered retrieval
• Define and track quality metrics (accuracy, completeness, error rates) and continuously improve pipeline performance
• Ensure secure handling of sensitive information, including automated redaction and compliance with governance standards

• Design and operate pipelines that convert raw, unstructured inputs into structured, template-aligned outputs using AI
• Map extracted knowledge to defined content model fields, ensuring outputs are complete, consistent, and production-ready
• Define structured capture methods (forms, schemas, workflows) to ensure key context (decisions, constraints, trade-offs) is captured
• Normalize and standardize data across sources and identify gaps to improve capture and transformation processes
• Define entity resolution and canonicalization rules to ensure concepts, terminology, and implementation knowledge are consistently represented across sources

• Ensure structured outputs support AI-driven use cases including vector search, retrieval-augmented generation (RAG), knowledge graph navigation, and downstream content generation
• Partner with the Content Model Lead to align transformation outputs with templates and structures
• Collaborate with Architecture and Engineering to align knowledge models, retrieval pipelines, and platform data models
• Define evaluation criteria for retrieval effectiveness, semantic relevance, and answer quality, and continuously improve knowledge performance through measurement and experimentation

• 8+ years of experience in knowledge management, information architecture, information systems, semantic technologies, data engineering, or related field
• Experience working with AI/LLM-based workflows in production
• Experience designing data pipelines, structured capture, or transformation processes
• Strong analytical skills with ability to define and improve quality metrics
• Experience working cross-functionally with product, engineering, and domain experts
• Experienced in using technologies such as Knowledge management platforms:
  Confluence, SharePoint, Notion Enterprise, Gainsight Knowledge, Guru
• AI / LLM:
  OpenAI / Azure
  
  OpenAI, Anthropic Claude, Google Gemini
• Agentic Workflow & Orchestration:
  ReAct (Reason + Act), Chain of Thought (CoT) patterns
• AI Operations:
  Prompt design and evaluation, LLM output evaluation and benchmarking, Model monitoring and QA, RAG evaluation frameworks (e.g., RAGAS), retrieval observability tools (e.g., Lang Smith, Tru Lens), Vector Databases, Markdown files
• Knowledge Modeling & Semantic Technologies:
  Taxonomy and ontology management platforms (e.g., Semaphore, Pool Party), knowledge graphs, entity resolution and semantic enrichment tools, graph exploration platforms (e.g., Neo4j Bloom)
• AI Extraction & Document Processing:
  Unstructured.io, Llama Parse, document intelligence and content extraction platforms
• Cloud environments:
  Azure, AWS, Google

• The Ideal Candidate Has built AI-driven knowledge capture or data pipelines at scale
• Can transform messy,…