Java Architect – AI Platforms & LLM Integration

Global Business Ser. 4u; New York (NY); Hybrid; USD 180,000 - 240,000; Part time

Job summary

Global Business Ser. 4u seeks a seasoned Java Architect for a 12–24 month contract in New York, NY. The role focuses on building scalable enterprise applications and integrating AI platform capabilities with LLM workflows.

You will drive design and architecture across Java, cloud services, and generative AI models, ensuring performance, security, and extensibility. Hybrid work requires 2-3 days onsite weekly and collaboration with cross-functional teams.

Qualifications

• 14+ years of Java/J2EE experience with Spring Boot and microservices.
• Cloud experience (AWS/GCP/Azure).
• Hands-on with LangChain, LlamaIndex or similar LLM toolchains.
• Knowledge of MCP and A2A middleware for enterprise systems.
• Containerization and orchestration with Docker/Kubernetes.
• Security, OAuth2 and data compliance understanding.
• Strong communication and leadership skills.

Responsibilities

• Architect and design enterprise-grade Java applications with AI/ML integration.
• Develop AI-enabled workflows using LangChain and LLM orchestration tools.
• Collaborate with data science to operationalize LLMs in production.
• Integrate systems using MCP, A2A, RESTful APIs and messaging queues.
• Define patterns for prompt chaining, agent workflows, and model routing.
• Ensure performance, scalability, and security across distributed environments.
• Provide guidance and reviews to development teams.
• Stay current with AI/LLM infrastructure advancements.

Skills

Java

Java architecture

Cloud platforms

LLM integration

REST APIs

Microservices

Security/OAuth2

Team leadership

Problem solving

Communication

Tools

LangChain

LLamaIndex

Agentic workflows

RAG pipelines

MCP

A2A

Docker

Kubernetes

OpenAI API

Anthropic API

Job description

Job Title: Java Architect – AI Platforms & LLM Integration

Job Type: 12–24 Month Project, Contract (C2C / W2 / 1099)

Location: New York, NY (Hybrid – 2-3 Days Onsite per Week)

Job Description

We are seeking a seasoned Java Architect with strong experience in building scalable enterprise applications and integrating AI platform capabilities. The ideal candidate will have deep understanding of AI toolchains, LLM-based frameworks (LangChain, Agentic systems), and enterprise middleware like MCP (Multi-Channel Platform) and A2A (Application-to-Application) integration. You will drive the design and architecture of intelligent enterprise applications that leverage Java, cloud services, and generative AI models, ensuring performance, security, and extensibility.

Key Responsibilities

• Architect and design enterprise-grade Java applications with integration of AI/ML components.
• Develop AI-enhanced workflows using LangChain, Agentic frameworks, and other LLM orchestration tools.
• Collaborate with data science and ML teams to operationalize LLMs in production.
• Integrate systems across platforms using MCP, A2A, RESTful APIs, and messaging queues.
• Define architectural patterns for prompt chaining, agent workflows, and model routing.
• Ensure system performance, scalability, and security across distributed environments.
• Provide guidance to development teams and perform code/architecture reviews.
• Stay current with advancements in AI/LLM infrastructure and integration frameworks.

Required Qualifications

• 14+ years of experience in Java/J2EE technologies, Spring Boot, REST APIs, Microservices.
• Experience designing scalable systems in cloud environments (AWS/GCP/Azure).
• Hands-on experience with LLM frameworks such as LangChain, LLamaIndex, Agentic workflows, or RAG pipelines.
• Strong understanding of MCP and A2A frameworks for enterprise communication and middleware.
• Experience with containerization and orchestration (Docker, Kubernetes).
• Solid understanding of security, identity management (OAuth2, SSO), and data compliance.
• Excellent problem-solving, communication, and leadership skills.

Preferred Qualifications

• Experience with LLM API integrations (OpenAI, Anthropic, etc.)
• Familiarity with vector databases (e.g., FAISS, Pinecone, Chroma).
• Experience with streaming platforms like Kafka.
• Knowledge of DevOps practices, CI/CD pipelines.

Prior experience mentoring or leading distributed engineering teams