Retrieval-Augmented Generation (RAG) Engineer

Ceed is a global headhunting firm specializing in elite AI talent recruitment . We partner with leading tech companies worldwide, connecting them with world-class AI engineers, architects, and specialists building tomorrow’s most impactful AI systems. This role offers the chance to work on high-profile projects shaping AI-powered knowledge automation and enterprise search.

The Role

We are hiring a Retrieval-Augmented Generation (RAG) Engineer to design, deploy, and optimize intelligent retrieval pipelines that combine large language models (LLMs) with external knowledge sources for highly reliable, context-rich AI applications.

You will :

• Design and build scalable RAG systems using vector databases, embedding models, and transformer-based LLMs.
• Develop semantic search pipelines for accurate, grounded responses across large document repositories.
• Integrate RAG solutions into chatbots, enterprise search platforms, and customer-facing products.
• Collaborate with AI, product, and data teams to reduce hallucinations, improve accuracy , and boost retrieval speed .
• Research and implement state-of-the-art retrieval and context injection strategies , staying ahead of AI architecture trends.
• Deploy production-grade RAG systems optimized for performance, latency, and reliability .

Ideal Profile

2+ years of experience in AI engineering, information retrieval, or NLP .

Strong skills in Python , with hands-on experience using frameworks such as LangChain, LlamaIndex, or Haystack .

Expertise with vector databases (Pinecone, Weaviate, Milvus) and semantic search techniques .

Familiarity with LLM APIs (OpenAI, Claude, etc.) and prompt engineering for RAG workflows .

Understanding of data pipeline architecture, embeddings, and transformer models .

Proactive, detail-oriented, and motivated to build highly reliable, production-grade AI retrieval systems .

What's on Offer?