AWS Bedrock Platform Engineer

Role Overview

We are seeking an experienced AWS Bedrock Platform Engineer to design, build, deploy, and operate secure, scalable, and production-ready Generative AI platforms using Amazon Bedrock and AWS cloud services. The ideal candidate will have strong hands-on experience with Bedrock, foundation model integration, RAG architectures, AI agents, platform automation, and enterprise security.

Key Responsibilities

• Design, deploy, and manage enterprise Generative AI platforms using Amazon Bedrock.
• Configure and manage foundation models, model access, inference profiles, and API integrations.
• Build and operationalize RAG pipelines using Bedrock Knowledge Bases, Amazon OpenSearch, and vector databases.
• Implement and manage Bedrock Agents, AgentCore, Guardrails, and model evaluation frameworks.
• Develop reusable GenAI platform components, APIs, SDKs, and integration frameworks.
• Implement secure multi-account and multi-tenant AI platform architectures.
• Automate infrastructure provisioning and deployments using Terraform, CloudFormation, and CI/CD pipelines.
• Implement AI security and governance, including IAM, KMS, VPC endpoints, data protection, and model access controls.
• Establish monitoring, logging, token usage tracking, cost optimization, and performance management.
• Support production deployments, troubleshooting, scalability, and platform reliability.

Required Skills

• AWS Bedrock: Foundation models, Knowledge Bases, Agents, AgentCore, Guardrails, inference APIs.
• Programming: Python, Boto3, REST APIs, AWS SDKs.
• GenAI Frameworks: LangChain, LangGraph, Strands Agents, or similar frameworks.
• RAG & Vector Databases: Amazon OpenSearch, pgvector, vector embeddings, semantic search.
• AWS Services: Lambda, API Gateway, S3, IAM, KMS, CloudWatch, Step Functions, ECS/EKS.
• Infrastructure as Code: Terraform or AWS CDK.
• DevOps: CI/CD, GitHub Actions, Jenkins, or AWS CodePipeline.
• Security: IAM policies, encryption, network isolation, guardrails, and enterprise AI governance.
• Observability: Model latency, token consumption, inference costs, tracing, and application monitoring.