GenAI Engineer: RAG, Vector Search & Databricks AI

Machine Learning Technologies, LLC; Houston (TX); On-site; USD 120,000 - 190,000; Full time

Job summary

Machine Learning Technologies, LLC in Houston is seeking an AI Engineer to design, build, and deploy enterprise Generative AI solutions on Databricks. You will work on RAG architectures, custom AI agents, document intelligence, and model serving to support real-world business use cases.

Collaborate with data engineers and developers to deliver end-to-end AI-powered products, implement evaluation frameworks, governance, and observability, and drive production deployment on Azure or AWS.

Qualifications

• Hands-on experience building enterprise GenAI solutions.
• Familiar with retrieval augmented generation and vector search.
• Experience deploying in regulated or enterprise environments.

Responsibilities

• Design and implement Generative AI and Agentic AI solutions.
• Build and optimize RAG architectures and vector search solutions.
• Develop custom AI agents and agent workflows.
• Implement document parsing, information extraction, and document intelligence capabilities.
• Create and maintain evaluation frameworks to assess AI solution quality, accuracy, and reliability.
• Design prompts and optimize prompt engineering strategies.
• Deploy and manage models using Databricks Model Serving and related MLOps capabilities.
• Integrate AI solutions with enterprise data platforms and applications.
• Collaborate with Data Engineers and Full Stack Developers to deliver end‑to‑end AI‑powered products.

Skills

Custom AI agents

Information extraction

Model serving

AI governance

Tools

Databricks Model Serving

Unity Catalog

Lakehouse architecture

Job description

Machine Learning Technologies, LLC in Houston is seeking an AI Engineer to design, build, and deploy enterprise Generative AI solutions on Databricks. You will work on RAG architectures, custom AI agents, document intelligence, and model serving to support real-world business use cases.

Collaborate with data engineers and developers to deliver end-to-end AI-powered products, implement evaluation frameworks, governance, and observability, and drive production deployment on Azure or AWS.