Generative AI Engineer: Agentic, Multimodal & RAG

XPath Solutions; Charlotte (NC); On-site; USD 140,000 - 190,000; Full time

Job summary

XPath Solutions is seeking a Generative AI Engineer in the Charlotte area to design, develop, and deploy enterprise Generative AI solutions. The role focuses on LLMs, Vision LLMs, vLLM inference, prompt engineering, RAG, and multimodal AI capable of production-grade deployments.

You will implement Agentic AI systems, manage sessions/memory, enable tool calling, and build scalable Python APIs to integrate GenAI into enterprise workflows while ensuring security and reliability.

Qualifications

• Strong proficiency in Python and modern AI frameworks.
• Experience with PyTorch and TensorFlow for large-scale models.
• Hands-on with vLLM inference and high-throughput serving.
• Familiarity with LLMs, Vision LLMs, and multimodal AI concepts.
• Experience building RAG pipelines and embedding-based retrieval.

Responsibilities

• Design and implement Generative AI solutions for text, image, and multimodal applications.
• Develop and optimize prompt engineering strategies to improve LLM performance, accuracy, and reliability.
• Build embedding-based retrieval systems and RAG pipelines.
• Develop Agentic AI applications: context management, memory handling, tool integration, and workflow orchestration.
• Deploy vLLM in production for high-throughput, low-latency inference.
• Build scalable Python APIs and integrate GenAI capabilities into enterprise workflows.
• Collaborate with cross-functional teams to deploy AI at scale, ensuring security and reliability.
• Explore and implement multi-agent AI systems and governance practices.

Skills

Python

PyTorch

TensorFlow

vLLM

Prompt engineering

Large Language Models

Vision LLMs

RAG

Embeddings

Agentic AI

Multimodal AI

AWS SageMaker

LangChain

LangGraph

LlamaIndex

CrewAI

AutoGen

API design

Tools

Python

Job description

XPath Solutions is seeking a Generative AI Engineer in the Charlotte area to design, develop, and deploy enterprise Generative AI solutions. The role focuses on LLMs, Vision LLMs, vLLM inference, prompt engineering, RAG, and multimodal AI capable of production-grade deployments.

You will implement Agentic AI systems, manage sessions/memory, enable tool calling, and build scalable Python APIs to integrate GenAI into enterprise workflows while ensuring security and reliability.