Staff AI Platform Engineer: Agent & Retrieval Infrastructure
Bedrockocean · Remote
About this role
## About Bedrock Ocean Bedrock Ocean builds and operates autonomous underwater vehicles (AUVs) that collect georeferenced ocean-floor data at commercial scale. We deliver bathymetric and imagery data products to customers through our platform, and we’re scaling toward continuous, around-the-clock data collection campaigns spanning months. We’re building AI agents on **Amazon Bedrock** to support our ocean data, internal operations, and customer platform. This role owns that architecture. > Note on names: **Amazon Bedrock** is the AWS service. **Bedrock Ocean** is us—unrelated, and we know it’s confusing. --- ## The Role We’re looking for a **Staff Platform Engineer** to lead our AI architecture. This goes beyond building agents on top of existing platforms—you’ll create the infrastructure itself, including: - orchestration layer - data and retrieval pipeline - security model for production data You’ll also build the tools and abstractions that let our engineering team implement AI features independently. This position combines software engineering, data engineering, and infrastructure operations. You’ll manage the full lifecycle of our Amazon Bedrock implementation—from initial data chunking to IAM access controls. Security is core to the role. Because agents with tool access are a new kind of system actor, you’ll define operational boundaries (what they can access, what they can do autonomously, and how they’re monitored). --- ## What You’ll Do - **Architect Agent Orchestration**: Design the Amazon Bedrock integration (agent/action group configuration, backend APIs, model access, throughput, and cross-environment deployment). - **Manage Retrieval Data Plane**: Own the end-to-end retrieval pipeline (ingestion → chunking → embeddings → storage in **Amazon OpenSearch Serverless**). Optimize for index design, cost, and capacity. - **Extend Data Pipelines**: Adapt ingestion pipelines for internal knowledge, ocean data, and customer platforms—especially for geospatial and large-binary datasets. - **Secure AI Infrastructure**: Implement robust security using **Bedrock Guardrails**, **VPC/PrivateLink**, least-privilege **IAM**, and audit trails for data isolation. - **Define Agent Governance**: Enforce approval boundaries for autonomous actions and ensure agents are safe and monitored. - **Establish LLMOps & Observability**: Implement monitoring for tracing, tool calls, and retrieval performance (e.g., **CloudWatch**, **Langfuse**, **Phoenix**). - **Build Evaluation Frameworks**: Create automated evaluation infrastructure, track results, and manage release gates for model accuracy. - **Enable Engineering Productivity**: Provide abstraction layers, SDKs, and self-service environments so engineers can ship AI features independently. - **Operational Excellence**: Manage environments as code across stages, ensure deployment safety, and participate in incident reviews. --- ## What We’re Looking For - **8+ years** in software and infrastructure engineering, with deep production backend experience (**Python or TypeScript preferred**, Go is fine) and staff-level ownership of technical direction. - Hands-on experience standing up **Amazon Bedrock** in production (agents, knowledge bases, guardrails, model access, throughput/quota decisions). - Containerized service deployment on **ECS, EKS, or Lambda**, with CI/CD you owned. - Practical **RAG** and vector search experience (embeddings, chunking strategies, semantic search quality, and operat
Listing freshness
CronJobs last confirmed this listing 2h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.