AI Data Engineer: LLMs, RAG & Multi-Agent Systems

Crossing Hurdles; United States; On-site; USD 140,000 - 190,000; Full time

Job summary

Crossing Hurdles is seeking an AI/ML engineer to design, implement, and optimize production-grade models using LLMs, RAG, and prompt engineering. You will develop multi-agent systems with LangGraph and LangChain, and deploy on secure cloud environments including AWS GovCloud, Google GovCloud, Azure IL5+, Vertex AI, and AWS Bedrock.

You will also build robust data pipelines, ETL processes, metadata catalogs, and ontologies to ensure data quality for AI training and inference, while creating REST

Qualifications

• Proven experience with Python for AI/ML development.
• Hands-on with LLMs, RAG systems, and prompt engineering in production.
• Familiarity with multi-agent orchestration and related frameworks.
• Deep understanding of cloud AI services (GovCloud, Vertex AI, Bedrock).
• Experience building data pipelines, ontologies, and ETL processes.

Responsibilities

• Design, implement, and optimize AI/ML models for production-grade apps.
• Develop and orchestrate multi-agent systems (LangGraph, LangChain).
• Deploy solutions on secure cloud environments (GovCloud, Vertex AI, Bedrock).
• Build data pipelines, ETL processes, and metadata catalogs for AI training/inference.
• Create and maintain REST APIs and SDK integrations for data/model access.
• Collaborate with product, security, and engineering teams to ensure secure DevOps practices.

Skills

Python for AI/ML

REST APIs & SDKs

LLMs & RAG in production

Multi-agent orchestration

Cloud AI services

Tools

LangGraph

LangChain

AWS GovCloud

Google GovCloud

Azure IL5+

Vertex AI

AWS Bedrock

Job description

Crossing Hurdles is seeking an AI/ML engineer to design, implement, and optimize production-grade models using LLMs, RAG, and prompt engineering. You will develop multi-agent systems with LangGraph and LangChain, and deploy on secure cloud environments including AWS GovCloud, Google GovCloud, Azure IL5+, Vertex AI, and AWS Bedrock.

You will also build robust data pipelines, ETL processes, metadata catalogs, and ontologies to ensure data quality for AI training and inference, while creating REST