Staff AI Platform Engineer: Agent Orchestration & Retrieval

Bedrock Ocean Exploration; United States; Remote; USD 160,000 - 220,000; Full time

Job summary

Bedrock Ocean is seeking a Staff Platform Engineer to lead the AI architecture and infrastructure. You will own the Amazon Bedrock integration, including agent orchestration, retrieval pipelines, and secure data boundaries.

This role blends software, data engineering, and infrastructure to scale production AI capabilities across internal and customer-focused data products. You will shape governance for autonomous agents, build LLMOps monitoring, and create abstractions that enable engineers to

Qualifications

• 8+ years in software and infrastructure engineering with backend focus.
• Hands-on experience standing up Amazon Bedrock in production: agents, knowledge bases, guardrails, model access.
• Containerized service deployment with CI/CD ownership (ECS, EKS, or Lambda).
• Experience with RAG and vector search, embeddings, and a managed vector database.
• Strong AWS ecosystem expertise: IAM, VPC, PrivateLink, S3, KMS, CloudWatch, IaC.

Responsibilities

• Architect Agent Orchestration for Bedrock integration and deployment.
• Own the end-to-end retrieval data plane from ingestion to storage (OpenSearch Serverless).
• Extend ingestion pipelines for knowledge, ocean data, and customer platforms.
• Define agent governance and safe autonomous actions.
• Implement LLMOps and observability with monitoring tools like CloudWatch, Langfuse, or Phoenix.
• Build evaluation frameworks and release gates for model accuracy.
• Provide SDKs and self-service environments for engineers to ship AI features.
• Manage the environment as code across stages for safe deployments.

Skills

Python

TypeScript

Go

AWS Bedrock

Tools

Amazon Bedrock

OpenSearch Serverless

Langfuse

Phoenix

Job description

Bedrock Ocean is seeking a Staff Platform Engineer to lead the AI architecture and infrastructure. You will own the Amazon Bedrock integration, including agent orchestration, retrieval pipelines, and secure data boundaries.

This role blends software, data engineering, and infrastructure to scale production AI capabilities across internal and customer-focused data products. You will shape governance for autonomous agents, build LLMOps monitoring, and create abstractions that enable engineers to