Onsite - AI Solution Architect - Generative AI, Agentic AI & Java - St. Louis, MO | New York, NY | Stamford, CT

We are seeking an experienced AI Solution Architect with strong expertise in enterprise architecture, Java, Generative AI, and Agentic AI. The ideal candidate will have hands-on experience implementing AI-powered solutions and designing scalable, secure, cloud-native applications using AWS., * Design and architect enterprise-grade AI/ML-powered applications using Java and AWS cloud services.

• Define architecture standards, design patterns, and best practices for integrating AI into Java-based ecosystems.
• Lead end-to-end architecture for microservices, APIs, event-driven systems, and data pipelines supporting AI/ML model serving.
• Design and implement Agentic AI and multi-agent solutions for enterprise environments.
• Architect LLM-powered applications using AWS Bedrock, OpenAI, or Anthropic Claude.
• Design Retrieval-Augmented Generation (RAG) solutions and integrate vector databases.
• Conduct architecture reviews, threat modeling, security assessments, and performance benchmarking.
• Optimize model inference, prompt engineering, prompt caching, and token consumption.
• Mentor senior engineers and provide technical leadership to cross-functional teams.
• Ensure scalability, reliability, security, and performance of enterprise AI applications.

Required Technical Skills

Java & Enterprise Architecture

• Core Java, Java 21+
• Spring Boot and Spring AI
• Enterprise application architecture and design patterns
• Microservices and distributed systems
• Event-driven architecture using Kafka, AWS SQS, and SNS
• REST and GraphQL API design
• gRPC architecture and design

Generative AI & Agentic AI

• Hands-on implementation of enterprise AI solutions
• Agentic AI and multi-agent frameworks
• Spring AI, LangGraph, Google ADK
• Agent-to-Agent (A2A) protocols and Model Context Protocol (MCP)
• LLM integration using Anthropic Claude, OpenAI, or AWS Bedrock
• Retrieval-Augmented Generation (RAG) architectures
• Vector databases such as OpenSearch, Pinecone, or pgvector
• Prompt engineering, prompt caching, and token optimization
• Model serving and inference optimization

AWS Cloud & Infrastructure

• Amazon Bedrock and Bedrock AgentCore
• EC2, ECS/EKS, AWS Lambda, and API Gateway
• S3, RDS, and Aurora
• IAM, KMS, and Secrets Manager
• VPC networking and cloud security
• Deployment and scaling of AI-powered cloud applications

This role requires an architecture-focused professional who can establish technical standards, lead end-to-end solution design, mentor senior engineers, and guide cross-functional teams in adopting AI-first architecture principles. Candidates must have practical implementation experience in at least one AI solution and a strong understanding of enterprise-scale AI integration., * 8-10 years of overall experience in software engineering and enterprise architecture.

• Strong architecture-level expertise in Core Java, Java 21+, Spring Boot, and microservices.
• Demonstrated hands-on experience implementing at least one AI-powered solution.
• Enterprise-level experience with Generative AI, Agentic AI, and LLM integration.
• Strong experience designing scalable, secure, cloud-native applications on AWS.
• Proven ability to lead architecture decisions, mentor senior engineers, and guide cross-functional teams.
• Excellent problem-solving, technical communication, and architectural decision-making skills.

Education

Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field.