Remote AI Engineer (RAG) - Grounded Gen & Vector Search
Posted Updated
Description
At BairesDev, a 100% remote role, we seek an AI Engineer specializing in RAG to design and implement advanced retrieval-augmented generation systems. You will connect external knowledge bases with LLMs to ground responses in domain data while minimizing hallucinations.
Responsibilities include building end-to-end RAG pipelines, managing vector databases, and refining chunking and reranking strategies. English proficiency and 4+ years of relevant experience are essential.
Design and implement end-to-end RAG pipelines, including ingestion, cleaning and embedding workflows. Manage high-performance vector databases for semantic and hybrid search. Develop chunking and reranking strategies to improve precision and context. Evaluate RAG systems with established benchmarks to ensure production readiness. Collaborate with data and software teams to integrate RAG into enterprise apps. Research and apply emerging RAG techniques like agentic RAG and context compression. 4+ years in AI engineering, ML or software engineering. Proven experience with Retrieval-Augmented Generation (RAG) architectures and hybrid search. Proficient in Python and vector databases (Pinecone, Qdrant, Weaviate). Hands-on with chunking, embeddings and reranking techniques. Familiar with evaluation frameworks such as RAGAS. Advanced English proficiency. 100% remote work Competitive USD or local currency pay Hardware & software setup for home Flexible hours Parental leave, vacations, holidays Global, multicultural environmentSkills
Sign in to read and join the discussion.