Development Lead - Advanced RPA

About the Role

We are looking for a GenAI Agentic Lead to drive the design, development, delivery, and governance of production-grade Generative AI and Agentic AI solutions. The role requires hands-on technical leadership in Large Language Models, RAG, Agentic RAG, multi-agent workflows, tool-calling architectures, LLMOps, Responsible AI, cloud AI services, and enterprise system integration. The candidate should be able to lead a team, define technical standards, guide solution architecture, mentor developers, and collaborate with business and technology stakeholders to deliver scalable, secure, and reliable AI-enabled applications. This role is suitable for candidates with a minimum of 5 years and up to 10–12 years of relevant experience in GenAI development, AI engineering, Python/backend development, ML/NLP applications, cloud AI services, enterprise automation, or technical leadership roles.

Key Responsibilities

Lead end-to-end design and delivery of GenAI, RAG, Agentic RAG, AI assistant, chatbot, document intelligence, and automation agent solutions. Define agentic AI architecture patterns including tool calling, function calling, planning, memory, reflection, multi-agent orchestration, workflow routing, and human-in-the-loop controls. Guide teams in building robust RAG pipelines covering ingestion, parsing, chunking, metadata design, embeddings, vector indexing, hybrid retrieval, reranking, query rewriting, and grounded response generation. Provide hands-on technical leadership using Python, APIs, microservices, LangChain, LangGraph, LlamaIndex, Semantic Kernel, AutoGen, CrewAI, or similar frameworks. Lead integration of LLMs with enterprise applications, knowledge repositories, databases, workflow platforms, search services, and cloud-based AI services. Establish standards for prompt engineering, prompt versioning, reusable prompt libraries, structured outputs, tool integration, evaluation datasets, and model configuration management. Drive LLMOps and GenAIOps practices including observability, tracing, monitoring, regression testing, latency optimization, token usage tracking, cost optimization, and production support readiness. Ensure Responsible AI, security, privacy, governance, access control, prompt injection mitigation, PII handling, auditability, and compliance controls are embedded in solution design. Review solution designs, code, prompts, retrieval logic, evaluation results, deployment plans, and production issues to maintain engineering quality. Mentor developers, conduct technical reviews, support estimation and planning, coordinate delivery, and communicate solution progress to stakeholders. Skill Requirements Mandatory Technical Skills Strong hands-on experience in Python , APIs, microservices, backend integration, modular application design, debugging, and production-grade development practices. Strong experience with Generative AI, Large Language Models, prompt engineering, embeddings, token management, structured outputs, and LLM-based application development . Hands-on experience designing and implementing RAG and Agentic RAG solutions using enterprise documents, knowledge repositories, vector databases, semantic search, hybrid retrieval, reranking, and grounded generation. Strong understanding of agentic AI concepts including planning, reasoning loops, tool calling, function calling, memory, autonomous workflows, multi-agent systems, supervisor-agent patterns, and human-in-the-loop design. Hands-on experience with agentic frameworks such as LangChain, LangGraph, LlamaIndex, Semantic Kernel, AutoGen, CrewAI , or equivalent orchestration frameworks. Experience integrating LLMs through cloud AI services and model APIs such as AWS Bedrock, Amazon SageMaker, Azure OpenAI, Google Vertex AI, OpenAI APIs, Anthropic APIs, or open-source model endpoints. Strong knowledge of vector databases or semantic search platforms such as FAISS, Pinecone, Chroma, Weaviate, OpenSearch, Azure AI Search, Qdrant, or pgvector. Working knowledge of LLMOps, GenAIOps, model evaluation, hallucination control, guardrails, observability, prompt/version management, and cost optimization practices. Ability to lead technical discussions, perform design reviews, mentor engineers, estimate work, manage technical risks, and communicate with stakeholders. Preferred / Additional Skills Experience leading GenAI delivery teams or technical workstreams for enterprise AI use cases. Exposure to AgentOps, AI gateways, MCP-based tool integration, GraphRAG, knowledge graphs, ontology-driven retrieval, or advanced reasoning patterns. Experience with FastAPI, Flask, Streamlit, React, Node.js, Docker, Kubernetes, CI/CD, and cloud deployment of AI-enabled applications. Knowledge of OCR, document intelligence, NLP, text classification, summarization, entity extraction, search, automation, and enterprise workflow use cases. Cloud or AI certifications across AWS, Azure, Google Cloud, Generative AI, Machine Learning, Data Science, or Solution Architecture are preferred.