Platform AI Architect

The Principal AI Architect will own the end-to-end architecture of the Agentic AI Platform across all layers including Meta-Agent, Orchestration, Agent Runtime, Memory/State, Tools, RAG, and Model layer. They will also define the technical blueprint, reusable patterns, AWS-native design, and multi-account strategy that power every agent in the platform.  Additionally, they will ensure the system is secure, scalable, well-governed, and aligned with enterprise standards for performance, reliability, and compliance.  Responsibilities

Architect the full Agentic Platform across AWS, Bedrock, LangChain/LangGraph, RAG, and Lakehouse components. 

Define multi-step agent patterns (ReAct, planning, routing) and reusable architecture templates. 

Own Bedrock model selection, embeddings strategies, knowledge bases, and guardrails design. 

Design AWS foundations: VPC, Subnets, IAM, KMS, Secrets Manager, CloudTrail, Config. 

Lead Lakehouse architecture: Glue, Athena, Lake Formation, S3 lakehouse patterns. 

Enforce structured output schemas, prompt architecture, and cross-account separation. 

Provide architectural sign-off for all agent workflows, tools, and platform extensions. 

••Ensure platform is scalable, observable, compliant, and optimized for cost and performance. 

Qualifications

Deep AWS architecture expertise. 

Proven experience building large-scale AI platforms. 

Expert-level agent design skills. 

Strong knowledge of AWS data stack. 

Ability to drive platform-wide standards. 

Demonstrated delivery in regulated industries.