LLM Engineer (RAG) – Remote

About the role

We are looking for an experienced LLM Engineer specialized in Retrieval‑Augmented Generation (RAG) to design and operate cutting‑edge systems that combine large language models with external knowledge sources. The role is fully remote and focuses on building high‑performance pipelines that deliver accurate, context‑aware responses.

Key responsibilities

• Design, deploy, and maintain vector database architectures using Pinecone, Qdrant, or Weaviate.
• Develop data ingestion pipelines, including chunking and embedding strategies for unstructured data.
• Implement reranking algorithms and hybrid search patterns to improve retrieval precision and recall.
• Build evaluation frameworks such as RAGAS to monitor and ensure response quality.
• Optimize the end‑to‑end RAG pipeline for low latency and high throughput in production.

Required profile

• 4+ years of experience in AI, data, or software engineering.
• Proven track record building and optimizing RAG pipelines and hybrid search solutions.
• Advanced proficiency in English.

Required skills

• Python programming.
• Experience with vector databases (Pinecone, Qdrant, Weaviate).
• Knowledge of embeddings, chunking, and reranking algorithms.
• Familiarity with evaluation frameworks such as RAGAS.

What we offer

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