Artificial Intelligence Engineer

AI Engineer

Profile Summary

AI Engineer focused on building and operating LLM-powered solutions for legal and regulatory document workflows (e.g., EU AI Act, DSA, Data Privacy, ESG, Security, Compliance). Strong emphasis on reference identification & resolution, retrieval quality, traceability, and evaluation in document-centric AI systems.

Core Responsibilities / Focus

• Design and implement GenAI / Agentic AI applications for complex document understanding and decision support
• Build RAG pipelines tailored to regulatory/legal texts (high precision, citation grounding, explainability)
• Develop robust ingestion and retrieval strategies, including contextual chunking, embeddings, and metadata enrichment
• Integrate Knowledge Graphs (RDF/SPARQL) with LLM workflows for structured + unstructured reasoning
• Orchestrate multi-step AI workflows using LangChain / LangGraph (and similar agent frameworks)
• Establish AI quality assurance and evaluation practices (e.g., retrieval quality, hallucination checks, judge-based evals, RAGAS-style scoring)
• Build & train / fine-tune specialized NER-related models
• Support model lifecycle activities (experimentation, versioning, deployment readiness, monitoring handover)

Core Skills (Must-Have)

• Python (primary)
• Docker / Docker Compose
• NLP / NLU
• GenAI / LLM application development
• Agentic AI
• RAG (Retrieval-Augmented Generation)
• Embeddings
• Contextual chunking strategies
• Knowledge Graphs (RDF)
• SPARQL
• Model lifecycle / ML application lifecycle
• LangChain
• LangGraph
• Git
• AI QA / evaluation (e.g., RAGAS, LLM judges, retrieval and answer quality validation)

Preferred / Nice-to-Have

• Java
• Kubernetes
• Dev Containers
• GitOps
• Documentation practices
• Deepagents (or similar advanced agent frameworks)

Domain Advantage

• Experience with legal, regulatory, compliance, and policy documents
• Understanding of requirements around auditability, explainability, and risk controls in AI systems