Python Backend Engineer for AI-Driven Scientific Data

CERN; Denmark; Hybrid; DKK 600,000 - 800,000; Full time

Benefits offered by this job

Hybrid work model

Job summary

CERN's Scientific Information Service in the OSI Department seeks a backend engineer to design, develop, and operate Python/Django applications, APIs, and data workflows for platforms used by researchers worldwide.

You will bring ML/AI capabilities into production, including semantic search, RAG, embeddings, and the Model Context Protocol, while collaborating with engineers and information specialists to build scalable, reliable systems.

Qualifications

• Master's degree or equivalent in Computer Science or related field.
• Strong experience in Python and backend development with Django.
• Experience with data-intensive applications or data processing workflows.
• Knowledge of modern Large Language Model technologies and AI integrations.
• Experience with Apache Airflow, React and TypeScript; OpenSearch/Elasticsearch is a plus.
• Experience with LLM applications, retrieval-augmented generation, embeddings and semantic search is a plus.

Responsibilities

• Develop, maintain, and operate backend applications, APIs, integrations, and data workflows.
• Integrate ML/AI capabilities into production systems using LLMs, RAG, and semantic search.
• Evaluate emerging AI technologies and apply them to scientific information use cases.
• Ensure software quality through automated testing, code review, monitoring, and CI.
• Collaborate with software engineers, product owners, and information specialists on architecture.

Skills

Python

Django

API design

Relational databases

Data-intensive apps

Airflow

OpenSearch

LLM integration

React/TypeScript

AI tooling

Education

Master's degree

Tools

Apache Airflow

React

TypeScript

OpenSearch

Elasticsearch

Model Context Protocol

Job description

CERN's Scientific Information Service in the OSI Department seeks a backend engineer to design, develop, and operate Python/Django applications, APIs, and data workflows for platforms used by researchers worldwide.

You will bring ML/AI capabilities into production, including semantic search, RAG, embeddings, and the Model Context Protocol, while collaborating with engineers and information specialists to build scalable, reliable systems.