AI, LLM & data
LLM orchestration, end-to-end RAG, vector stores, and the databases behind them.
What it covers
- Pipeline RAG de bout en bout : embeddings, indexation, base vectorielle, reranking, évaluation.
- Orchestration de plusieurs services LLM derrière une API Gateway unifiée.
- APIs Claude et OpenAI, prompt engineering, pgvector.
The proofs
A skill is not written, it is aggregated. Every line points to the mission that demonstrates it, with its period.