Senior Python AI Data Engineer - RAG & AI Data Platform

Intellias; Poland; On-site; PLN 447,000 - 670,000; Full time

Job summary

Intellias seeks a Senior Python / AI Data Engineer for a London-based client in investment management to advance enterprise AI initiatives. You will design and implement scalable data platforms and RAG pipelines that securely discover, retrieve, and reason over trusted enterprise data.

You will build and evaluate LLM-based extraction and knowledge graphs, supporting regulated financial services with robust data governance and provenance.

Qualifications

• 5+ years of production Python development.
• 2+ years of production LLM/RAG engineering.
• Experience with retrieval pipelines, vector stores, and structured extraction.
• Experience with LLM tooling and evaluation frameworks.

Responsibilities

• Build and optimize production-grade RAG and retrieval pipelines.
• Maintain hybrid retrieval with keyword and semantic capabilities.
• Develop LLM/RAG evaluation frameworks and release gates.
• Create structure-aware document processing including OCR and multilingual content.
• Build scalable LLM-based extraction pipelines with schemas and confidence scoring.
• Design and maintain PostgreSQL models, JSONB structures, migrations, and derived views.
• Implement document provenance, citations, lineage, and temporal views.
• Collaborate with client and engineering teams in a regulated financial-services environment.

Skills

Python development

LLM/RAG engineering

Retrieval pipelines

PostgreSQL

Data provenance

Knowledge graphs

AI agents

English communication

Education

Bachelor's degree in CS/Engineering/Data Science

Tools

Langfuse

RAGAS

DeepEval

Job description

Intellias seeks a Senior Python / AI Data Engineer for a London-based client in investment management to advance enterprise AI initiatives. You will design and implement scalable data platforms and RAG pipelines that securely discover, retrieve, and reason over trusted enterprise data.

You will build and evaluate LLM-based extraction and knowledge graphs, supporting regulated financial services with robust data governance and provenance.