Context

At CAST the world leader in Software Intelligence, we are building the foundation to ground AI with AAA data — Aggregated, Accurate, and Augmented — sourced from real-world software and technology projects.

We go beyond manual curation: this role is about using AI to empower AI.
You will design intelligent pipelines leveraging LLMs, embeddings, and NLP tools to clean, enrich, and validate data, ensuring that AI systems and autonomous agents can rely on it for training, reasoning and contextual understanding.

Your Mission

As a Data Engineer specialized in AI Enablement, you will be responsible for building robust, intelligent, and traceable data pipelines that power AI models and agents with high-quality, semantically rich information.

Your Responsibilities:

• Aggregate and structure data from diverse software ecosystems (codebases, APIs, tickets, documentation, architecture specs).

• Apply LLMs, embeddings, and NLP techniques to automate data cleaning, entity extraction, metadata tagging, and semantic annotation.

• Build and maintain semantic data pipelines for LLM fine-tuning and Retrieval-Augmented Generation (RAG).

• Organize datasets for Agent-to-Agent (A2A) interactions using APIs, vector databases, and knowledge graphs.

• Collaborate with AI research and engineering teams to evolve schemas, prompts, labeling strategies, and evaluation datasets.

• Ensure data lineage, reproducibility, and version control across all workflows.

Your Profile

We’re looking for a hands-on Data Engineer who understands both the rigor of data pipelines and the creativity of AI enablement.
You’re analytical, curious, and passionate about leveraging AI to make data smarter.

Core Qualifications

• Degree from a leading engineering school (Grande École) or equivalent university program.

• 3+ years of experience in data engineering, ML data operations, or structured data curation.

• Proficiency in Python and data pipeline tools (Pandas, PyArrow, regex, Airflow).

• Experience with LLM or NLP frameworks (Hugging Face, spaCy, LangChain).

• Ability to use AI to clean, enrich, classify, and organize technical or unstructured content.

• Strong understanding of tokenization, chunking, and model input preparation.

• Experience working with software project data (Git repositories, APIs, documentation).

Bonus Skills

• Knowledge of vector databases (FAISS, Qdrant, Weaviate) or knowledge graphs (Neo4j, RDF, SPARQL).

• Exposure to agentic AI or autonomous AI frameworks (LangChain Agents, AutoGPT, OpenAgents).

• Experience with RAG architectures, LLMOps, or prompt pipelines.

• Background in software engineering or technical documentation.

Recruitment Process

Our recruitment process consists of three steps:

• Initial interview with our HR team.

• Discussion with Guillaume, our Product Management Director, and Christophe, our R&D Director.

• Final meeting to share our decision and next steps.

• With us, the recruitment process moves quickly and efficiently!

Why Join Us?

• Be part of a global AI innovation hub shaping the next generation of Software Intelligence.

• Work at the intersection of data, AI, and software engineering, with real-world impact.

• Collaborate with top AI experts and contribute to groundbreaking initiatives in AI enablement and automation.