Start searching
Back to Jobs
Recently postedTechnology

AI Architect - Agentic AI & MCP

Acunor InfotechSan Jose, CA🇺🇸United States

Quick overview

SeniorityMid Senior
Work modeOn Site
LocationSan Jose, CA, United States
DockerMicroservicesAWSMLOpsGoogle CloudLLMPythonAzureKubernetesTypeScriptPrompt EngineeringCI/CDLangChainLangGraphRAG

Job description

AI Architect Agentic AI & Model Context Protocol (MCP)
Location: San Jose, CA
Work Arrangement: Hybrid 3 Days Onsite per Week
Employment Type: Contract / C2C
Job Overview
We are seeking an experienced and hands-on AI Architect specializing in Agentic AI, Multi-Agent Systems, and Model Context Protocol (MCP) to design, develop, and scale enterprise-grade AI solutions.
The ideal candidate will possess deep technical expertise in Large Language Models (LLMs), autonomous AI agents, multi-agent orchestration, and modern AI development frameworks. This position requires a strong combination of architectural leadership and hands-on engineering capabilities, with a focus on building secure, scalable, and production-ready AI systems.
The AI Architect will collaborate with engineering teams, business stakeholders, and technology leaders to establish AI architecture standards, develop reusable frameworks, and accelerate enterprise AI adoption.
Key Responsibilities
Agentic AI & Multi-Agent Architecture
  • Design, develop, and implement scalable Agentic AI solutions using frameworks such as LangGraph, AutoGen, and CrewAI.
  • Architect multi-agent systems supporting autonomous decision-making, task delegation, agent collaboration, and workflow orchestration.
  • Develop mechanisms for agent state management, contextual memory, autonomous negotiation, and secure inter-agent communication.
  • Establish reusable architecture patterns for building reliable, scalable, and maintainable AI agent ecosystems.
Model Context Protocol (MCP) & Enterprise Integrations
  • Design, develop, and maintain MCP servers and clients to enable seamless integration between LLMs, enterprise applications, APIs, databases, and development tools.
  • Implement standardized tool-calling mechanisms and context-sharing capabilities across AI applications.
  • Build secure integration frameworks supporting authentication, authorization, data access, and enterprise governance.
  • Optimize MCP-based integrations for scalability, performance, reliability, and interoperability.
LLM Application Development & AI Engineering
  • Architect and develop production-grade applications powered by Large Language Models.
  • Implement Retrieval-Augmented Generation (RAG), prompt engineering, vector search, and contextual retrieval solutions.
  • Develop AI workflows integrating foundation models, enterprise knowledge repositories, and external services.
  • Write production-ready code, develop prototypes, and contribute directly to AI application development.
  • Implement evaluation, monitoring, testing, and optimization strategies to improve AI system accuracy, reliability, and performance.
AI Platform Architecture & Cloud Engineering
  • Design scalable AI development platforms supporting model experimentation, training, testing, deployment, and lifecycle management.
  • Architect cloud-native AI solutions using AWS, Microsoft Azure, or Google Cloud Platform.
  • Leverage Docker, Kubernetes, and modern AI SDKs to build containerized and scalable AI services.
  • Establish architectural standards for high-throughput, low-latency AI applications.
  • Implement AI engineering best practices covering observability, security, performance optimization, and deployment automation.
Technical Leadership & Collaboration
  • Lead technical architecture discussions, design reviews, and engineering workshops.
  • Develop architecture documentation, technical design specifications, and Requests for Comments (RFCs).
  • Provide hands-on technical guidance and mentorship to AI engineers and software development teams.
  • Collaborate with cross-functional stakeholders to translate business requirements into scalable AI solutions.
  • Evaluate emerging AI frameworks, technologies, and architectural approaches to drive continuous innovation.
Required Qualifications
  • 10+ years of experience in software engineering, solution architecture, or enterprise application architecture.
  • 3+ years of hands-on experience developing and deploying production-grade LLM applications and AI systems.
  • Strong expertise in Agentic AI and multi-agent orchestration frameworks, including LangGraph, AutoGen, or CrewAI.
  • Proven experience designing and implementing Model Context Protocol (MCP) servers, clients, or comparable AI tool-integration protocols.
  • Strong understanding of autonomous agents, task orchestration, state management, contextual memory, and inter-agent communication.
  • Hands-on experience with Retrieval-Augmented Generation (RAG), prompt engineering, embeddings, and vector databases.
  • Strong programming proficiency in Python, TypeScript, or Go.
  • Experience developing AI applications using modern LLM APIs, frameworks, and SDKs.
  • Hands-on experience with AWS, Azure, or Google Cloud Platform, including cloud-native application architecture.
  • Strong understanding of Docker, Kubernetes, microservices, and distributed systems.
  • Experience designing scalable, secure, and highly available enterprise AI platforms.
  • Excellent communication, technical documentation, and architectural decision-making skills.
  • Ability to work onsite in San Jose, CA, three days per week.
Preferred Qualifications
  • Experience developing enterprise AI platforms or reusable Agentic AI frameworks.
  • Familiarity with LangChain, LlamaIndex, Semantic Kernel, or similar AI development frameworks.
  • Experience integrating AI agents with enterprise applications, APIs, databases, and external tools.
  • Knowledge of LLM evaluation frameworks, observability, guardrails, and responsible AI practices.
  • Experience with AI/ML deployment pipelines, CI/CD, and MLOps/LLMOps practices.
  • Understanding of distributed AI architectures, event-driven systems, and asynchronous processing.
  • Experience optimizing AI applications for latency, throughput, scalability, and operational cost.

Similar jobs

Apply