RPA Developer - Core (IN)
HCLTech
HCLTech
This role focuses on designing, developing, and deploying intelligent applications powered by cutting-edge Generative AI technologies. You will leverage Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and autonomous agent frameworks to build sophisticated AI solutions. The position requires robust programming skills and practical experience in GenAI application development, with an emphasis on integrating LLMs with enterprise data sources, APIs, and cloud services.
This is an ideal opportunity for individuals looking to contribute to AI assistants, advanced chatbots, knowledge search systems, and document intelligence solutions. The role offers the chance to build production-ready GenAI features with a strong focus on accuracy, reliability, safety, cost-effectiveness, and performance. The ideal candidate will have 1-4 years of relevant experience, though candidates with strong project portfolios, internships, or demonstrable skills in Python and GenAI are encouraged to apply.
Key responsibilities include developing GenAI applications using Python, LLM APIs, prompt engineering, and RAG patterns. You will build AI agents capable of complex reasoning, planning, tool execution, and multi-step task completion. Designing and implementing RAG pipelines involving document ingestion, semantic search, and grounded response generation is crucial.
Integration of GenAI solutions with diverse enterprise data sources, including documents, databases, and knowledge bases, will be a primary focus. You will also create robust prompt templates, implement tool integrations for API calls and workflow execution, and support model selection based on specific use case requirements.
Additional duties involve creating reusable components for prompt management, retrieval, and monitoring, as well as performing thorough testing and evaluation of GenAI outputs for accuracy, relevance, and safety. Basic Responsible AI and security controls will be implemented, and collaboration with cross-functional teams to deliver AI-enabled features is essential. Documentation of all aspects of the GenAI solutions is also a key requirement.
A strong foundation in Python programming, including data structures, APIs, OOP, and debugging, is mandatory. Practical experience with Generative AI concepts such as LLMs, prompt engineering, embeddings, and AI application development is essential.
Working knowledge of RAG architecture, encompassing document processing, vectorization, and semantic search, is required. Experience or strong project exposure to agentic AI concepts like tool calling, planning, memory, and autonomous execution is vital. Familiarity with agentic development frameworks such as LangChain, LangGraph, LlamaIndex, or similar tools is expected.
Proficiency in integrating LLMs via APIs or cloud AI services (e.g., AWS Bedrock, Azure OpenAI) and working knowledge of vector databases (e.g., Pinecone, Chroma) are necessary. Understanding of REST APIs, JSON, backend integration, and basic application deployment, along with Git and Agile methodologies, are also required.
HCLTech
IT Consulting