Full Stack LLM Development Team Lead/Consultant

Accenture seeks a Full Stack LLM Development Team Lead/Consultant in Gurugram for a full-time Custom Software Engineer project role. The position provides hands-on technical leadership in designing and delivering production-ready generative AI and agentic AI solutions. The posting states a minimum of 5 years of experience and describes the ideal candidate as having 6–10 years of software development experience. It requires 15 years of full-time education.

Responsibilities

• Lead the design and development of AI agents, agentic workflows, orchestration, LLM integrations, APIs and enterprise integrations.
• Translate business requirements into scalable solutions; guide implementation, conduct design and code reviews, resolve complex issues, and maintain quality, security, performance and maintainability.
• Mentor developers and promote coding standards, reusable components, testing, observability and Responsible AI practices.

Required expertise:

• Strong Python development skills for production-ready applications, including REST APIs, architecture, design patterns, testing, debugging and performance optimization.
• Practical GenAI and LLM application experience covering prompt engineering, context management, model selection, tokens, embeddings and tool or function calling.
• Hands-on agent and workflow development with frameworks such as LangChain, LangGraph, AutoGen, CrewAI, Semantic Kernel or Amazon Bedrock Agents; understanding of RAG, vector databases, semantic search and knowledge retrieval. Experience integrating with APIs, enterprise applications, databases and external tools is also required.

Preferred or desirable exposure includes MCP, multi-agent architectures, Amazon Bedrock, OpenAI, Anthropic or Azure OpenAI services, AI evaluation, guardrails, AI security, Docker, Kubernetes, serverless or cloud deployment, observability and production support.