Enterprise AI Architect for Scalable LLM & RAG Systems

Veriipro; Lake Saint Louis (MO); Hybrid; USD 140,000 - 210,000; Full time

Job summary

Veriipro is seeking an Artificial Intelligence Architect to design and implement scalable AI-driven architectures. You will lead the integration of AI/ML capabilities, agentic AI frameworks, and multi-agent orchestration across enterprise systems.

Key responsibilities include architecting microservices, event-driven flows with Kafka/SQS/SNS, and building robust REST/GraphQL APIs with gRPC. Expertise in LLM integration, vector databases, and model serving is essential.

Qualifications

• Java 21+ and Spring Boot expertise with Spring AI.
• Experience in designing and implementing microservices and event-driven architectures (Kafka, SQS/SNS).
• Proficient in REST/GraphQL API design and gRPC communication.
• Strong understanding of design patterns, enterprise architecture and scalable systems.
• Experience with AI/ML integration, agentic AI and multi-agent frameworks at enterprise scale.
• Proficiency in LLM integration using Claude, OpenAI, or AWS Bedrock.
• Knowledge of RAG architectures and vector databases (OpenSearch, Pinecone, pgvector).
• Model serving, inference optimization and prompt engineering.
• Familiarity with AWS services and cloud-native architectures.

Skills

Java

Cloud Architecture

AI/ML Integration

Agentic AI

Multi-agent frameworks

Enterprise architecture

Design patterns

Prompt engineering

Model serving

Tools

Java 21+

Spring Boot

Spring AI

Kafka

SQS/SNS

REST

GraphQL

gRPC

Anthropic Claude API

OpenAI

AWS Bedrock

OpenSearch

Pinecone

pgvector

Job description

Veriipro is seeking an Artificial Intelligence Architect to design and implement scalable AI-driven architectures. You will lead the integration of AI/ML capabilities, agentic AI frameworks, and multi-agent orchestration across enterprise systems.

Key responsibilities include architecting microservices, event-driven flows with Kafka/SQS/SNS, and building robust REST/GraphQL APIs with gRPC. Expertise in LLM integration, vector databases, and model serving is essential.