Agentic AI Architect

We are looking for an experienced Agentic AI Architect to design and build intelligent AI agents and multi-agent systems. The candidate should have strong expertise in Generative AI, Large Language Models (LLMs), agent orchestration frameworks, and Model Context Protocol (MCP). The role involves designing scalable AI solutions that can reason, plan, use tools, interact with external systems, and automate complex business workflows.

Responsibilities:

• Design and develop scalable Agentic AI architectures and multi-agent systems.
• Build AI agents using LangChain, LangGraph, and LangSmith.
• Implement Model Context Protocol (MCP) for connecting AI agents with external tools, APIs, databases, and enterprise systems.
• Develop LLM-powered applications using models such as GPT, Claude, Gemini, or open-source LLMs.
• Design RAG (Retrieval-Augmented Generation) pipelines using vector databases.
• Implement agent planning, reasoning, memory management, tool calling, and workflow orchestration.
• Build secure and reliable AI solutions with guardrails, human-in-the-loop approvals, and error handling.
• Integrate AI applications with REST APIs, enterprise platforms, cloud services, and databases.
• Optimise AI systems for latency, scalability, cost, accuracy, and performance.
• Establish best practices for AI security, observability, evaluation, monitoring, and deployment.
• Lead technical discussions, mentor engineers, and collaborate with business and product teams.

Required Technical Skills:

• Agentic AI: AI agents, multi-agent systems, agent orchestration, planning and reasoning.
• Frameworks: LangChain, LangGraph, LangSmith, AutoGen, CrewAI or similar.
• MCP: MCP servers, MCP clients, tools, resources, and enterprise integrations.
• Programming: Strong Python programming skills; FastAPI or Flask.
• LLMs: OpenAI, Azure OpenAI, Anthropic Claude, Gemini, or open-source models.
• GenAI: Prompt engineering, function calling, structured outputs, RAG, embeddings, and LLM evaluation.
• Vector Databases: Pinecone, FAISS, Chroma, Weaviate, or Milvus.
• Cloud: AWS, Microsoft Azure, or Google Cloud Platform.
• Architecture: Microservices, REST APIs, distributed systems, Docker, Kubernetes, and CI/CD.
• Security: AI guardrails, access control, data privacy, and responsible AI practices.