AI Engineer — RAG & LLM Systems, Multi-Agent

VDart; Frisco (TX); On-site; USD 131,000 - 200,000; Full time

Job summary

A leading technology firm is seeking a Mid-Senior AI Engineer to architect and deploy intelligent systems using advanced techniques like RAG and Large Language Models. The ideal candidate will have extensive experience in full-stack development and a strong focus on generative AI. Responsibilities include designing RAG pipelines, applying chunking strategies, and collaborating on scalable AI solutions. Candidates should possess deep expertise in Python and relevant MLOps tools. This contract position is based in Frisco, TX.

Qualifications

• 8 to 12 years of experience as a Full‑stack developer.
• At least 2 to 4 years in generative AI or RAG systems.
• Experience with MLOps tools: MLflow, Docker, CI/CD.

Responsibilities

• Design and implement RAG pipelines.
• Apply chunking strategies for optimization.
• Finetune and evaluate LLMs for various tasks.
• Build multi‑agentic systems.
• Integrate AI capabilities into enterprise applications.
• Collaborate with stakeholders for scalable solutions.
• Ensure model reliability and ethical compliance.

Skills

Full-stack development

Generative AI or RAG systems

Chunking techniques

Embedding strategies

MLflow

Docker

CI/CD pipelines

Prompt engineering

Model evaluation

Python

AI solutions

SDLC lifecycle

Partner client communications

Job description

A leading technology firm is seeking a Mid-Senior AI Engineer to architect and deploy intelligent systems using advanced techniques like RAG and Large Language Models. The ideal candidate will have extensive experience in full-stack development and a strong focus on generative AI. Responsibilities include designing RAG pipelines, applying chunking strategies, and collaborating on scalable AI solutions. Candidates should possess deep expertise in Python and relevant MLOps tools. This contract position is based in Frisco, TX.