Job
In this role, you will design and implement knowledge graph architectures, develop AI-driven data pipelines for entity enrichment, and build a conversational interface for compliance analysts.
Job summary
This listing has been machine translated. Show original
Job technologies
Your role in the team
- As an AI Engineer, you will own the AI and data layer of the platform. You will design and implement the knowledge graph architecture, build agentic pipelines that enrich entity data through AI-powered web research, and develop the graph interrogation layer that translates natural-language compliance questions into structured graph queries.
- You will work closely with the CTO and a small AI team including a data engineer and a junior AI engineer. You will have significant technical autonomy and direct influence over how the product evolves.
- Own and evolve the platform's knowledge graph data model - entities (Company, Person, Community, Episodic), relationships, and temporal attributes.
- Implement and extend custom entity and relationship extraction pipelines using LMs, with structured output validation and confidence scoring.
- Use Graphiti (Zep AI’s temporal knowledge graph framework) as the memory layer, managing episode ingestion, entity resolution, and graph updates.
- Design and enforce graph schema standards, ensuring consistency across data sources and ingestion pipelines.
- Build evaluation frameworks to measure extraction quality, entity disambiguation accuracy, and graph coverage.
- Design and implement multi-step agentic workflows that orchestrate LLM calls, web search, database lookups, and graph writes.
- Integrate AI web search (Tavily, Perplexity, or similar) as a tool within agentic pipelines for real-time entity enrichment.
- Build retrieval-augmented generation (RAG) pipelines over the knowledge graph, translating compliance queries into Cypher and natural language answers.
- Implement the graph interrogation layer—a conversational interface that enables compliance analysts to query the knowledge graph without writing Cypher.
- Manage LLM API integrations (Anthropic Claude, Gemini), including prompt engineering, structured outputs, and cost and latency optimization.
- Build and maintain Python-based data ingestion pipelines that read from Databricks, connect to external APIs (sanctions lists, corporate registries, Polixis, Vantage), and write to Neo4j.
- Implement NER (named entity recognition) and entity disambiguation logic for extracting structured facts from unstructured compliance documents.
- Develop topic modeling pipelines to classify extracted facts as knowledge graph relationship attributes.
- Integrate with the .NET backend via well-defined HTTP contracts, ensuring the AI layer is independently deployable and testable.
- Stay current with the fast-moving agentic AI and knowledge graph literature - evaluate new frameworks, models, and techniques for production applicability.
- Contribute to architectural decisions with evidence: benchmarks, prototypes, and documented trade-offs.
- Maintain Claude Code context files (CLAUDE.md, SKILLS.md) for the AI codebase, enabling AI-augmented development across the team.
- Write clear technical documentation in Notion covering design decisions, data models, and operational runbooks.
Our expectations of you
Qualifications
- Deep familiarity with LLM APIs (OpenAI, Anthropic, or Gemini) — prompt engineering, structured outputs, function/tool calling, and cost management.
- Understanding the trade-offs between LLMs and smaller fine-tuned models (Hugging Face Transformers, sentence-transformers)—knowing when a purpose-built model outperforms a prompted general-purpose model in terms of cost, latency, and accuracy.
- Python proficiency – you write clean, testable Python and understand async patterns for I/O-bound AI workloads.
- Ability to read and apply AI research papers—you can take a paper on narrative extraction or entity disambiguation and turn it into a working prototype.
- Strong English communication skills, both written and verbal.
- Familiarity with entity resolution and disambiguation techniques at scale.
- Knowledge of the third-party risk, sanctions screening, or KYC/AML domain.
- Exposure to GCP (Vertex AI, Cloud Run, Pub/Sub, Cloud Storage).
- Prior work in a RegTech, FinTech, or compliance-adjacent environment.
Experience
- 3+ years of professional experience in AI/ML engineering, with at least 1 year working on knowledge graphs or graph-based data systems in production.
- Hands-on experience with Neo4j – data modeling, Cypher query writing, schema design, and performance tuning.
- Experience building agentic pipelines - multi-step LLM workflows with tool use, memory, and state management.
- Experience with RAG architectures—vector search, hybrid retrieval, and integrating retrieval into LLM-powered applications.
- Direct experience with or knowledge of Graphiti (Zep AI) or other temporal knowledge graph frameworks.
- Experience with NER pipelines, topic modeling, or information extraction from compliance or financial documents.
- Experience with Databricks, Delta Lake, or similar data lakehouse platforms.
- Experience designing evaluation frameworks for LLM-generated structured outputs.
What we offer
- Control Risks bietet ein wettbewerbsfähiges Vergütungs- und Leistungspaket, das transparent gestaltet und im vollständigen Stellenangebot zusammengefasst ist.
- We operate a discretionary global bonus scheme that incentivises and rewards individuals based on company and individual performance.
- Control Risks unterstützt, wo immer möglich, hybride Arbeitsmodelle, die den Wert persönlicher Begegnungen im Büro und mit unseren Kunden betonen und zugleich flexibles und ortsunabhängiges Arbeiten ermöglichen.
- Working with our clients, our people are given direct responsibility, career development opportunities, and the chance to collaborate on fascinating projects in a rewarding and inclusive global environment from day one.
- The Company is committed to advancing its diversity, inclusion and equity agenda. As an employee, you have access to various business resource groups, including the Company’s LGBT+ network, MOSAIC; the Women’s Network; and Synergy, a people network that celebrates and promotes ethnic diversity at Control Risks.
Topics you will work on
Job locations
About your employer
Control Risks Group Holdings Ltd provides comprehensive risk and strategy consulting on an international level, focusing on security and compliance issues. The company helps organizations operate safely and in compliance with regulations.
- Established Company
- Onsite, Hybrid
- Consulting
More jobs
These jobs might also interest you
You’ll be joining at a stage where we’re building and evolving our new CRM platform. That’s exactly what makes this role special: you won’t just develop features—you’ll actively help shape the technical foundation of a modern CRM ecosystem. Together...
Hello, let's say WE! We - the HUK-COBURG Insurance Group - are among the top 10 in Germany. Founded over 90 years ago, we are now the leading insurer for private households with over 13 million customers and the largest German auto insurer. Our...
The role As a Forward Deployed AI Engineer, you go directly into our specialist departments, understand the processes, and develop production-ready AI and automation solutions that will fundamentally change the way the entire GGW Group operates. You do...
