Title

Scalable Knowledge Graph Construction from Multimodal Enterprise Data

Objective

Develop a pipeline that takes unstructured, multimodal input (PDFs, images, websites, technical manuals, etc.) and produces a structured knowledge graph representing the internal knowledge of a company — covering processes, products, components, etc.

Scope & Challenges

• Handle multiple input formats (text, tables, diagrams, layout-aware PDF parsing, OCR).
• Extract and normalize entities and relations with provenance and confidence scores.
• Support tenant isolation, scalability to multiple companies/domains.
• Output must conform to a predefined schema/ontology usable by downstream systems.

Dataset

• Provided in-house by the organization.
• Includes real-world enterprise documentation (PDFs, technical images, etc.).
• A small gold-labeled subset may be manually annotated for evaluation.

Deliverables

• A reproducible pipeline that:
• Parses and extracts structured knowledge from unstructured inputs.
• Assembles a multi-tenant knowledge graph in a defined intermediate format.
• API or export mechanism for downstream consumption.
• Evaluation report with extraction accuracy (precision/recall), provenance quality, and performance benchmarks.

About Hypertype

We’re building the next generation of AI products and AI Agents in the Customer Support space. Focused on manufacturing but with clients across other sectors like fintech, health tech and more we are giving hundreds of companies across the globe the capacity to transform their customer journey with the latest advancements in AI. Our customers proudly recognise us for delivering the "highest quality answers in the market... outsmarting Gemini, Fin, Microsoft Copilot etc". —a testament to our unwavering commitment to excellence and precision in every interaction.

We are a group of people that work the extra mile together, that fearlessly push the boundaries to new heights and that deeply own what they deliver. We look for those who are ambitious, humble and fast to build together things humankind has not witnessed yet.