RAG Engineer – Remote

About the role

As a Retrieval‑Augmented Generation (RAG) Engineer at BairesDev, you will design and deploy end‑to‑end pipelines that combine large language models with advanced information‑retrieval architectures. The role is fully remote and focuses on delivering context‑aware, high‑accuracy AI solutions for global clients.

Key responsibilities

• Architect, build, and maintain scalable RAG pipelines from data ingestion to inference.
• Design indexing strategies and optimize vector search to achieve sub‑second retrieval speeds.
• Integrate large language models (LLMs) with vector databases and ensure seamless prompt engineering.
• Develop evaluation frameworks to continuously improve grounding and response accuracy.
• Collaborate with cross‑functional engineering teams to embed generative AI capabilities into production applications.

Required profile

• 5+ years of experience in software or AI engineering.
• Proven track record of designing and deploying RAG pipelines.
• Strong understanding of generative AI architectures, LLMs, and prompt engineering.
• Advanced proficiency in English.

Required skills

• Retrieval‑Augmented Generation (RAG) pipeline development
• Vector databases and information‑retrieval systems
• Large Language Models (LLMs)
• Prompt engineering
• Generative AI architectures

What we offer

• 100% remote work from anywhere
• Competitive compensation in USD or local currency
• Provided hardware and software setup for home office
• Flexible schedule and paid parental leave, vacations, national holidays
• Mentorship, skill development, and growth opportunities within a multicultural global team