- Berlin, Berlin, Germany
- Hybrid
- Full-time · Senior
- 3+ years
Own the AI and data layer of the platform, designing and implementing the knowledge graph architecture, building agentic pipelines for entity data enrichment, and developing the graph interrogation layer for natural language compliance queries.
Compensation
Control Risks offers a competitively positioned compensation and benefits package that is transparent and summarised in the full job offer. We operate a discretionary global bonus scheme that incentivises, and rewards individuals based on company and individual performance.
Responsibilities
- Own and evolve the platform’s knowledge graph data model
- Implement and extend custom entity and relationship extraction pipelines using LMs
- Use Graphiti (Zep AI’s temporal knowledge graph framework) as the memory layer
- Design and enforce graph schema standards
- Build evaluation frameworks to measure extraction quality, entity disambiguation accuracy, and graph coverage
Requirements
- Nice to have: Graphiti (Zep AI)
- Nice to have: Entity resolution and disambiguation
- Nice to have: NER pipelines
- Nice to have: Topic modelling
- Nice to have: Third-party risk