About This Role
AI/RAG Engineer — Dallas, TX | Full-Time | On-Site
—
About the Company
A leading applied GenAI company at the forefront of building production-grade retrieval-augmented generation systems for real-world enterprise use cases. This team ships products that reach actual users — not prototypes that live in a lab. If you want to work where cutting-edge AI meets rigorous engineering, this is that place.
—
The Role
This is a hands-on engineering role for someone who has genuinely taken a RAG-powered application from concept to production. You will own meaningful portions of the retrieval pipeline, contribute to the application layer, and collaborate closely with a team that cares deeply about the quality of what it ships. If you have spent the past year or two building in the applied GenAI space and can speak fluently to the trade-offs involved at every stage of a retrieval system, this role was designed for you.
—
What You Will Do
Design and implement end-to-end RAG pipelines, making deliberate decisions around chunking strategies, embedding model selection, and retrieval architecture. Tune retrieval performance through reranking, relevance scoring, and iterative experimentation to ensure outputs meet production quality standards. Build and maintain robust FastAPI-based services with proper authentication patterns, API gateway integration, and secure, scalable data flows. Work with MongoDB and Redis to support both persistent storage and high-performance caching needs across the application stack. Collaborate with cross-functional teammates to translate product requirements into reliable, well-tested AI-powered features. Participate in design discussions and contribute informed opinions on system architecture, model selection, and pipeline trade-offs.
—
What We Are Looking For
• 1+ years in applied GenAI or RAG engineering
• Proven experience shipping end-to-end RAG pipelines to production
• Strong command of embedding model selection and trade-off analysis
• Hands-on with semantic search and retrieval tuning techniques
• Experience with reranking strategies and relevance optimization
• Proficiency in FastAPI for building production API services
• Working knowledge of MongoDB and Redis
• Solid understanding of JWT-based auth and API Gateway patterns
The ideal candidate is a product-minded engineer who has moved beyond calling LLM APIs and has real ownership experience across the full retrieval stack — from how documents are chunked and embedded to how results are ranked and surfaced to end users. You should be comfortable discussing the reasoning behind your architectural choices, not just the implementation. A background in a team actively shipping to users, rather than a research or prototyping context, will set you apart.
—
Nice to Have
• Experience with Angular or React front-end frameworks
• Background in pre-LLM search or information retrieval systems
• Familiarity with data pipeline design and orchestration
Candidates who bring front-end exposure in Angular or React will find opportunities to contribute across a broader surface area of the product. Prior experience with classical search and retrieval systems — before the LLM era — is a genuine asset, as it signals a deeper understanding of retrieval fundamentals that makes for stronger RAG engineers. These are not requirements, but they add meaningful dimension to an already strong application.
—
What We Offer
This is a full-time, on-site position based in Dallas, TX. You will be joining a focused, high-output team working on problems that are genuinely at the frontier of applied AI. The environment rewards engineers who take initiative, think critically about product quality, and want to grow alongside a company building something that matters. There is real opportunity here to deepen your expertise, take on increasing ownership, and shape the direction of systems that reach real users at scale.