RAG Engineer / Generative AI Engineer

Remote
Retrieval-Augmented Generation | LLMs | Vector Databases | AI Pipelines

About the Role

We're hiring a RAG Engineer / Generative AI Engineer to build and scale production-grade Retrieval-Augmented Generation (RAG) pipelines using Large Language Models (LLMs). This role focuses on high-performance retrieval systems, vector databases, AI DevOps, and deployment in real-world, client-facing environments.

This is a full-time, 6-month contract opportunity for someone who thrives in fast-paced AI engineering teams.

What You'll Do

1. RAG Pipeline Engineering

• Design and optimize RAG architectures, including document ingestion, chunking, tokenization, and normalization.
• Configure and fine-tune embedding models and manage vector databases to ensure low-latency retrieval.
• Implement retrieval logic optimization, freshness rules, and data decay strategies.
• Build automated re-indexing pipelines, safety guardrails, and refusal logic for out-of-distribution or outdated queries.

2. Technical Search & AI Discovery

• Expand and optimize backend website architectures for machine readability and AI-driven search.
• Ensure web properties support effective indexing, retrieval, and semantic discovery.

3. AI DevOps & Deployment

• Deploy AI features across Development, UAT, and Production environments.
• Build scalable, client-facing AI pipelines that support high-volume usage.
• Maintain AI engineering standards including prompt versioning, schema control, and reproducibility.

Required Qualifications

• Bachelor's / Master's degree in Computer Science, Engineering, Data Science, Artificial Intelligence, or a related technical field (or equivalent practical experience).
• Strong hands-on experience with Generative AI, Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG).
• Solid understanding of vector search, embeddings, and semantic retrieval systems.
• Experience building and deploying production AI pipelines.
• Familiarity with AI observability, evaluation, and monitoring tools.
• Background in search engineering, information retrieval, or ML infrastructure.
• Ability to operate in fast-paced, client-facing environments.
• Available to work full-time.

Why Join Us?

• Work on real-world LLM and RAG systems in production.
• High ownership and technical impact.
• Exposure to client-facing AI deployments.
• Opportunity to shape scalable AI architecture from the ground up.