Lead Agentic AI Engineer

Lead Agentic AI Engineer

Job Title -  Lead Agentic AI Engineer - Level 9 - ACS Song

Management Level: Level 9 – Lead/Specialist

Location: Kochi

Must have skills: AWS Bedrock/Azure AI Foundry/ Google Vertex

Good to have skills:

Experience: 5-8 years of experience is required

Educational Qualification: Graduation (Accurate educational details should capture)

Job Summary

We are seeking an Agentic AI Developer with hands-on experience in building AI agents, LLM-powered applications, and intelligent workflow automation solutions using platforms such as AWS Bedrock, Azure AI Foundry, or GCP Vertex AI. The ideal candidate should have 1–2 years of practical experience in Agentic AI and a strong foundation of at least 5 years in backend development or data engineering. This role will focus on designing, developing, and integrating agent-based systems that can reason, plan, retrieve information, use tools, communicate with other agents, and automate complex business workflows. The candidate will work closely with architects, product teams, data engineers, and application developers to deliver scalable, secure, interoperable, and production-ready AI solutions

Roles and Responsibilities

• Build and support production-grade Agentic AI solutions using cloud-native AI platforms such as AWS Bedrock, Azure AI Foundry, or GCP Vertex AI. 
• Design intelligent agents capable of tool use, workflow orchestration, retrieval-augmented generation, reasoning, task automation, memory management, and multi-agent collaboration. 
• Apply strong backend development or data engineering experience to create scalable APIs, data pipelines, integrations, agent tools, and AI-enabled applications. 
• Enable secure and interoperable agent ecosystems using standards and protocols such as MCP and A2A for tool connectivity, context access, and agent-to-agent communication. 
• Design, develop, and maintain Agentic AI applications using AWS Bedrock, Azure AI Foundry, or GCP Vertex AI. 
• Build AI agents that can perform planning, reasoning, tool calling, memory management, workflow automation, and multi-step task execution. 
• Implement integrations using Model Context Protocol — MCP to enable agents and LLM applications to securely connect with external tools, APIs, enterprise systems, databases, and data sources. 
• Work with Agent2Agent — A2A patterns or protocols to support agent discovery, agent-to-agent communication, task delegation, and multi-agent collaboration. 
• Develop backend services, APIs, connectors, and integrations to enable AI agents to interact with enterprise applications, databases, documents, and external systems. 
• Implement Retrieval-Augmented Generation solutions using vector databases, embeddings, document processing, semantic search, and knowledge retrieval patterns. GraphRAG experience is a plus. 
• Work with LLM frameworks and orchestration tools such as LangChain, LangGraph, Semantic Kernel, LlamaIndex, AutoGen, CrewAI, Strands or equivalent technologies. 
• Evaluate, test, and improve agent performance, including prompt quality, response accuracy, latency, reliability, guardrails, security, and cost efficiency. 
• Debug and resolve issues related to agent behavior, API integrations, tool execution, MCP servers or clients, A2A communication flows, data retrieval, workflow failures, model responses, and production deployments. 
• Collaborate with architects, product owners, backend developers, data engineers, and DevOps teams while following best practices for testing, CI/CD, monitoring, documentation, and secure deployment

Professional and Technical Skills:

• 1–2 years of hands-on experience in Agentic AI, LLM application development, AI agents, RAG-based solutions, GenAI workflow automation, or multi-agent systems. 
• Minimum 5 years of professional experience in backend development, data engineering, or a combination of both. 
• Experience building production-grade applications, APIs, data pipelines, automation workflows, enterprise integrations, or cloud-native services. 
• Hands-on experience or implementation exposure with MCP — Model Context Protocol for connecting AI agents or LLM applications with tools, APIs, enterprise systems, and external data sources. 
• Hands-on experience or working knowledge of A2A — Agent2Agent Protocol or similar agent interoperability patterns for enabling communication, coordination, and collaboration between AI agents. 
• Prior experience working in cloud-based environments and deploying scalable, reliable, and secure solutions
• Hands-on experience with at least one major AI cloud platform: AWS Bedrock, Azure AI Foundry, or GCP Vertex AI. 
• Strong understanding of Agentic AI concepts such as tool calling, planning, reasoning, memory, multi-agent workflows, orchestration, autonomous task execution, and agentic workflow design. 
• Experience working with MCP clients, MCP servers, tool registration, tool execution, context retrieval, and secure integration of external systems with LLM applications. 
• Experience with A2A-based or multi-agent communication patterns, including agent discovery, capability exchange, task handoff, inter-agent messaging, and collaborative workflow execution. 
• Experience with LLM application frameworks such as LangChain, LangGraph, Semantic Kernel, LlamaIndex, AutoGen, CrewAI, or similar frameworks. 
• Strong programming skills in Python; experience with Java, Node.js, or other backend technologies is an added advantage. 
• Experience developing backend services, REST APIs, microservices, event-driven applications, or integration layers. 
• Good understanding of Retrieval-Augmented Generation, embeddings, vector search, semantic search, chunking strategies, document ingestion, and prompt engineering. 
• Familiarity with vector databases or search platforms such as Azure AI Search, Amazon OpenSearch, Pinecone, Weaviate, FAISS, Chroma, Milvus, or similar tools. 
• Experience with Git-based development, code reviews, CI/CD pipelines, Docker, logging, monitoring, authentication, authorization, secrets management, and secure API integration. 
• Strong experience designing and developing scalable backend systems, services, APIs, data processing solutions, or enterprise integration layers. 
• Ability to integrate AI agents with databases, enterprise applications, third-party APIs, internal services, workflow systems, and external tools using protocols such as MCP where applicable. 
• Experience with data ingestion, transformation, validation, metadata handling, structured data processing, and unstructured document processing. 
• Good understanding of system design, performance optimization, error handling, observability, and production support. 

Additional Information      

Behavioral and Collaboration Skills 

• Strong analytical, troubleshooting, and problem-solving skills. 
• Ability to work effectively with architects, product owners, data engineers, backend developers, DevOps teams, and business stakeholders. 
• Strong communication skills (English) with the ability to explain AI concepts, technical designs, limitations, and implementation approaches clearly. 
• Proactive mindset with ownership of assigned features, production issues, experimentation, and continuous improvement. 
• Comfortable working in agile teams and participating in sprint planning, technical discussions, demos, code reviews, and implementation activities. 

About Our Company | Accenture (do not remove the hyperlink)