AI/LLM Engineer: Bedrock, RAG & Prompt Engineering

Xforia Global Talent & Technology Solutions; Marysville (OH); On-site; USD 120,000 - 160,000; Full time

Job summary

Xforia Global Talent & Technology Solutions is seeking a skilled AI/ML engineer to design and implement LLM-based applications and RAG pipelines. You will architect agentic workflows, fine-tune prompts, and ensure scalable, secure AI services across the stack.

Responsibilities include integrating foundation models via AWS Bedrock, building vector search and retrieval pipelines with OpenSearch, Pinecone, or similar DBs, and deploying robust APIs using Python (FastAPI/Flask) or Node.js.

Qualifications

• Experience designing and implementing LLM-based applications.
• Experience with AWS Bedrock and AWS AI services.
• Experience building retrieval and vector-search pipelines with OpenSearch/OpenSearch-compatible or Pinecone-like systems.

Responsibilities

• Design and implement LLM-based applications and RAG pipelines.
• Integrate foundation models via AWS Bedrock and manage model guardrails.
• Build and optimize vector search and retrieval pipelines (OpenSearch, Kendra, Pinecone).
• Implement agent orchestration frameworks for multistep reasoning tasks.
• Build scalable APIs and microservices using Python (FastAPI/Flask) or Node.js.

Skills

ASP.NET MVC

Prompt Engineering

Python

API design

Tools

AWS Bedrock

AWS AI Services

OpenSearch

Kendra

Pinecone

LangChain

LangGraph

Bedrock Agents

FastAPI

Flask

EC2

EKS

SageMaker

API Gateway

Lambda

S3

DynamoDB

RDS

Aurora

Job description

Xforia Global Talent & Technology Solutions is seeking a skilled AI/ML engineer to design and implement LLM-based applications and RAG pipelines. You will architect agentic workflows, fine-tune prompts, and ensure scalable, secure AI services across the stack.

Responsibilities include integrating foundation models via AWS Bedrock, building vector search and retrieval pipelines with OpenSearch, Pinecone, or similar DBs, and deploying robust APIs using Python (FastAPI/Flask) or Node.js.