Senior Full Stack AI Engineer (RAG / LLM) [h31x7]

Talantir; France; Remote; EUR 54,000 - 120,000; Full time

Benefits offered by this job

Remote-first culture

Flexible working hours

Company apartments in Europe

Job summary

Talantir is seeking an experienced Full Stack AI Engineer to build an AI platform for corporate structure assessments using RAG, search, and LLM reasoning. You will develop backend services in Python, design end-to-end RAG pipelines, and implement hybrid search with Azure AI Search / Qdrant.

You’ll process documents, generate reports, and support internal tools with Streamlit and Node.js/React. The role is remote-first with flexible working culture and opportunities across Europe; pay range

Qualifications

• 5+ years Python experience
• Experience with LLMs, embeddings and OpenAI APIs
• Familiarity with vector databases and retrieval systems
• Knowledge of async processing (Celery, messaging)
• Basic Node.js / React for integration

Responsibilities

• Build backend services in Python (FastAPI)
• Develop end-to-end RAG pipelines (ingestion → retrieval → generation)
• Implement hybrid search (vector + BM25) using Azure AI Search / Qdrant
• Process complex documents (PDF, OCR, structured chunking)
• Generate structured outputs (Excel/Word reports)
• Support internal tools with Streamlit and integrate with Node.js / React

Skills

Python

Backend engineering

LLMs & embeddings

RAG pipelines

Async processing

Node.js/React

Vector databases

Tools

FastAPI

Qdrant

Azure AI Search

LangChain

Streamlit

Node.js

React

Celery

Job description

We are looking for an experienced Full Stack AI Engineer to work on a new project. We’re building an AI platform to automate complex corporate structure assessments using *RAG, search, and LLM reasoning*. This replaces manual, time-intensive work done by accounting and legal teams with a scalable, auditable system.

What You’ll Do

• Build backend services in *Python (FastAPI)*
• Develop *end-to-end RAG pipelines* (ingestion → retrieval → generation)
• Implement *hybrid search* (vector + BM25) using *Azure AI Search / Qdrant*
• Process complex documents (PDF, OCR, structured chunking)
• Generate structured outputs (Excel/Word reports)
• Support internal tools with *Streamlit* and integrate with *Node.js / React*

Requirements

• Strong Python and backend engineering experience
• Hands-on with *RAG, embeddings, and LLMs (OpenAI APIs)*
• Experience with *vector databases and retrieval systems*
• Familiarity with *async processing (Celery, messaging)*
• Basic Node.js / React for integration

Nice to Have

• Azure AI Search
• RAG evaluation frameworks
• LangChain / multi-agent systems

*What We Offer*

• Attractive salary
• Large freedom and real influence
• No unhealthy competition, team approach to meeting challenges
• Remote-first, flexible working culture
• Company apartments in cool cities across Europe: work and enjoy a memorable getaway

About Us

We are a software house with 18 years of experience and a global portfolio of projects. We help businesses modernize, scale, and innovate through custom software solutions. Our team embraces unconventional ideas and new technologies, delivering solutions with real impact. If you value professionalism, creativity, and a strong engineering culture, you'll feel at home here.

Job Type: Full-time

Pay: 54,000.00€ - 120,000.00€ per year

Experience:

• Python: 5 years (required)
• AI: 3 years (required)

Work Location: Remote