Location: Europe (Remote)

Contract: Freelance (6-12 months)

THE COMPANY

Our client is a recruitment consultancy specializing in IT, Finance, HR, and Digital Technology.

We are seeking an experienced Python Developer with strong hands-on experience in Artificial Intelligence (AI), Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and AI agents to join a remote project focused on developing an AI-driven document analysis platform. The successful candidate will be responsible for building scalable AI-powered solutions, integrating LLMs, developing document processing pipelines, implementing intelligent retrieval systems, and designing multi-agent workflows.

RESPONSIBILITIES

• Develop and maintain AI-powered applications using Python, LLMs, RAG architecture, and AI agents.

• Design and implement provider-agnostic interfaces for LLMs and embedding models.

• Build document ingestion pipelines, including PDF parsing, OCR, intelligent chunking, metadata extraction, and vector indexing.

• Implement hybrid retrieval systems combining semantic search and keyword-based search.

• Develop AI agents with structured inputs, defined schemas, and validated outputs.

• Integrate embedding models and vector databases into AI applications.

• Design evaluation frameworks to measure retrieval quality, classification accuracy, citation validity, and LLM performance.

• Optimize prompts and AI workflows to improve accuracy, reliability, and efficiency.

• Ensure compliance with AI security, data governance, and data residency requirements.

• Collaborate with technical teams and subject matter experts to translate business requirements into AI solutions.

• Produce clear technical documentation.

REQUIREMENTS

· 3–5 years of professional experience in Python development or software engineering.

· Strong proficiency in Python.

· Mandatory hands-on experience developing AI applications using LLMs and RAG.

· Practical experience with AI agents and agent-based workflows.

· Experience working with embeddings, vector databases, and semantic search.

· Knowledge of prompt engineering and LLM evaluation techniques.

· Experience processing unstructured documents, including PDFs and OCR.

· Familiarity with AI security, governance, and data protection principles.

· Strong problem-solving skills and ability to work independently.

· Technical engineering background or equivalent relevant qualification.

· Good command of English.

· European Union citizenship is mandatory.

VALUEABLE

Experience with some of the following technologies will be highly valued:

· AI frameworks: LangChain, LangGraph, LlamaIndex, CrewAI.

· LLMs: OpenAI, Azure OpenAI, Anthropic Claude, open-source models.

· Vector databases: Pinecone, FAISS, ChromaDB, Weaviate, Qdrant.

· Embeddings: Sentence Transformers, Hugging Face, OpenAI Embeddings.

· Document processing: PyMuPDF, pdfplumber, Tesseract OCR, Unstructured.

· AI evaluation: Ragas, DeepEval, LangSmith.

· Backend development: FastAPI, REST APIs.