Backend Agentic Architect

We are looking for an experienced Backend + Agentic AI Architect to design and build scalable backend platforms and intelligent agentic AI systems. The candidate will be responsible for backend architecture, AI agent orchestration, LLM integrations, APIs, microservices, data platforms, and enterprise-grade AI solutions. Key Responsibilities Design and architect scalable, secure, and high-performance backend systems. Architect Agentic AI solutions capable of planning, reasoning, tool usage, and autonomous task execution. Design multi-agent workflows and AI agent orchestration frameworks. Develop backend services and APIs using Python, Java, Node.js, or similar technologies. Integrate LLMs, foundation models, vector databases, RAG pipelines, and AI tools into enterprise applications. Design RESTful APIs, microservices, event-driven architectures, and asynchronous processing. Build agent tool integrations with enterprise applications, databases, APIs, and external services. Design RAG architectures, including document ingestion, embeddings, chunking, retrieval, and re-ranking. Implement memory, context management, state management, and agent communication mechanisms. Work with frameworks such as LangChain, LangGraph, LlamaIndex, Semantic Kernel, or similar technologies. Design AI systems with appropriate guardrails, security, observability, evaluation, and human-in-the-loop controls. Lead technical design discussions and define architecture standards and best practices. Optimize application performance, scalability, reliability, and cloud costs. Collaborate with product managers, data scientists, ML engineers, and development teams. Mentor engineers and provide technical leadership throughout the development lifecycle. Mandatory Skills Strong experience in Backend Architecture and Software Engineering. Hands-on experience building Agentic AI / LLM-based applications. Strong proficiency in Python and/or Java/Node.js. Experience with REST APIs, microservices, API gateways, and distributed systems. Strong understanding of LLMs, prompt engineering, RAG, embeddings, and vector databases. Experience with LangChain/LangGraph, LlamaIndex, Semantic Kernel, or equivalent agent frameworks. Experience with PostgreSQL/SQL and NoSQL databases. Experience with vector databases such as Pinecone, Milvus, Weaviate, pgvector, or Chroma. Strong knowledge of cloud platforms – AWS, Azure, or GCP. Experience with Docker, Kubernetes, CI/CD, and DevOps practices. Strong understanding of security, authentication, authorization, and API security. Good to Have