AI Engineer

Control Risks

. Own and evolve the platform’s knowledge graph data model covering entities, relationships, and temporal attributes .

Posted 11/7/2026full-timeBerlin • GermanyMid-LevelSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in AI/ML engineering with a strong focus on knowledge graph data modeling, entity extraction, and LLM integration. Proficient in Python and Neo4j, with a solid understanding of compliance-related frameworks and evaluation methodologies.

Highest-signal resume keywords

AI/ML EngineeringKnowledge GraphsNeo4j Data ModellingPython ProficiencyLLM Integration

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Knowledge Graph Data ModelEntity Extraction PipelinesCypher Query WritingPrompt EngineeringNER PipelinesTopic ModellingEvaluation FrameworksRAG ArchitecturesData Ingestion PipelinesGraph Schema Design

Soft Skills

Strong English Communication Skills

Tools & Technologies

Neo4jGraphitiDatabricksGCPAnthropic ClaudeGeminiTavilyPerplexityHugging Face TransformersDelta Lake

Industry Keywords

RegTechFinTechComplianceKYC/AMLThird-Party RiskSanctions Screening

Tech Stack

Tools & technologies

CloudGoogle Cloud PlatformNeo4jPython.NET

About the role

Key responsibilities & impact

Own and evolve the platform’s knowledge graph data model covering entities, relationships, and temporal attributes
Implement and extend custom entity and relationship extraction pipelines using language models, structured output validation, and confidence scoring
Use Graphiti as the temporal knowledge graph memory layer, managing episode ingestion, entity resolution, and graph updates
Design and enforce graph schema standards across data sources and ingestion pipelines
Build evaluation frameworks for extraction quality, entity disambiguation accuracy, and graph coverage
Design and implement multi-step agentic workflows orchestrating LLM calls, web search, database lookups, and graph writes
Integrate AI web search tools such as Tavily or Perplexity for real-time entity enrichment
Build RAG pipelines over the knowledge graph, translating compliance queries into Cypher and natural-language answers
Implement a conversational graph interrogation layer for compliance analysts
Manage Anthropic Claude and Gemini integrations, including prompt engineering, structured outputs, and cost/latency optimization
Build and maintain Python data-ingestion pipelines from Databricks and external APIs into Neo4j
Implement NER and entity-disambiguation logic for unstructured compliance documents
Develop topic-modelling pipelines to classify extracted facts as knowledge-graph relationship attributes
Integrate the AI layer with the .NET backend through well-defined HTTP contracts
Evaluate emerging agentic AI and knowledge graph frameworks, models, and techniques
Contribute to architecture decisions using benchmarks, prototypes, and documented trade-offs
Maintain Claude Code context files for the AI codebase
Write technical documentation in Notion covering design decisions, data models, and operational runbooks
Work closely with the CTO, data engineer, and junior AI engineer with significant technical autonomy

Requirements

What you’ll need

3+ years of professional experience in AI/ML engineering
At least 1 year working on knowledge graphs or graph-based data systems in production
Hands-on experience with Neo4j, including data modelling, Cypher query writing, schema design, and performance tuning
Deep familiarity with LLM APIs such as OpenAI, Anthropic, or Gemini
Experience with prompt engineering, structured outputs, function/tool calling, and cost management
Understanding of trade-offs between LLMs and smaller fine-tuned models, including Hugging Face Transformers and sentence-transformers
Experience building agentic pipelines with multi-step LLM workflows, tool use, memory, and state management
Python proficiency, including clean, testable Python and async patterns for I/O-bound AI workloads
Experience with RAG architectures, vector search, hybrid retrieval, and LLM application integration
Ability to read and apply AI research papers
Strong English communication skills, written and verbal
Direct experience or knowledge with Graphiti (Zep AI) or other temporal knowledge graph frameworks is a strong advantage
Familiarity with entity resolution and disambiguation techniques at scale is a strong advantage
Experience with NER pipelines, topic modelling, or information extraction from compliance or financial documents is a strong advantage
Knowledge of third-party risk, sanctions screening, or KYC/AML is a strong advantage
Experience with Databricks, Delta Lake, or similar data lakehouse platforms is a strong advantage
Exposure to GCP, including Vertex AI, Cloud Run, Pub/Sub, and Cloud Storage, is a strong advantage
Experience designing evaluation frameworks for LLM-generated structured outputs is a strong advantage
Prior work in a RegTech, FinTech, or compliance-adjacent environment is a strong advantage
CV must be submitted in English

Benefits

Comp & perks

Discretionary global bonus scheme based on company and individual performance
Hybrid working arrangements
Flexible and remote working support
Direct responsibility from day one
Career development opportunities
Collaborative work on fascinating projects
Rewarding and inclusive global environment
Access to business resource groups, including MOSAIC, the Women's Network, and Synergy
Equal opportunity employer
Reasonable interview adjustments available