AI AWS Bedrock Engineer

AI AWS Bedrock Engineer

Quick Facts

Location: Marysville, Ohio

Description

Design and implement LLM-based applications including RAG pipelines, agentic workflows, and fine-tuning using Amazon Bedrock. Integrate foundation models with model selection guardrails and evaluation, and build scalable AI services delivered through APIs and microservices. Optimize performance and cost for AI workloads while ensuring security with authentication and role-based access control.

Responsibilities

• Design and implement LLM-based applications covering RAG pipelines, agentic workflows, fine-tuning, and prompt engineering.
• Integrate foundation models via Amazon Bedrock, including model selection, guardrails, and evaluation.
• Build and optimize vector search and retrieval pipelines using OpenSearch, Kendra, or vector databases such as Pinecone.
• Orchestrate agents for multi-step reasoning using LangChain, LangGraph, and/or Bedrock Agents.
• Develop scalable APIs and microservices with Python (FastAPI/Flask) or Node.js.
• Implement data pipelines for training and inference data preparation using AWS Glue/EMR or Python ETL.
• Manage containerized workloads using ECS/EKS and build UI layers that consume backend AI services.
• Implement real-time streaming responses for chat-style AI interfaces.
• Integrate authentication using Amazon Cognito and role-based access control.
• Architect solutions using core AWS services such as Bedrock, SageMaker, Lambda, API Gateway, S3, DynamoDB, RDS/Aurora, ECS/EKS, and Step Functions.
• Set up CI/CD pipelines using CodePipeline/CodeBuild or GitHub Actions and AWS deployment.
• Manage cost optimization for AI workloads, including token usage monitoring, model routing, and caching strategies via ElastiCache.

Requirements

• Mandatory skills: ASP.NET MVC, AWS AI Services, AWS Bedrock, and Prompt Engineering.
• Proven experience designing and implementing LLM-based applications (RAG, agent workflows, and prompt engineering).
• Hands-on experience integrating and evaluating foundation models with Bedrock, including guardrails.
• Experience building vector search and retrieval pipelines on AWS or with third-party vector databases.
• Experience using agent orchestration frameworks such as LangChain and LangGraph (or Bedrock Agents).
• Ability to build scalable backend services and APIs using Python (FastAPI/Flask) or Node.js.
• Knowledge of AWS services for end-to-end ML application architecture (Lambda, API Gateway, S3, DynamoDB, RDS/Aurora, Step Functions, ECS/EKS, SageMaker).
• Experience with authentication and RBAC using Amazon Cognito.
• Experience implementing CI/CD with CodePipeline/CodeBuild or GitHub Actions.
• Ability to implement cost optimization practices for AI workloads (token monitoring, routing, caching).

Benefits

Benefits were not specified in the provided job posting.