Senior RPA Developer - Core (IN)
HCLTech
HCLTech
This role focuses on designing, building, and deploying intelligent applications powered by advanced Generative AI technologies. You will work with Large Language Models, Retrieval-Augmented Generation (RAG), and autonomous agents to create sophisticated AI solutions. The position requires a strong foundation in programming and hands-on experience with GenAI development. You will be instrumental in connecting LLMs with enterprise data, APIs, and cloud services to develop AI assistants, chatbots, knowledge search tools, and automation agents. The goal is to deliver production-ready GenAI features with robust controls for accuracy, reliability, safety, and performance.
Ideal candidates will have 1 to 4 years of relevant experience. Those new to the field are encouraged to apply if they possess significant project work, internships, certifications, or a strong GitHub/portfolio presence showcasing skills in Python, GenAI, LLM applications, RAG, prompt engineering, or agentic workflows.
Key duties involve developing GenAI applications using Python, LLM APIs, prompt engineering, and RAG patterns. You will build AI agents capable of complex reasoning, planning, and multi-step execution, including tool and function calling. Designing and implementing RAG pipelines, from document ingestion to grounded response generation, is crucial. You'll integrate these solutions with diverse enterprise data sources and systems. Responsibilities also include creating and managing prompt templates, tool integrations, reusable components, and implementing responsible AI and security controls. Testing, evaluation, and documentation of GenAI outputs and processes are essential. Collaboration with cross-functional teams and stakeholders is vital for successful delivery.
A strong programming background in Python, including data structures, APIs, OOP, and debugging, is mandatory. Hands-on experience with Generative AI, LLMs, prompt engineering, embeddings, and AI application development is required. You must have working knowledge of RAG architecture and agentic AI concepts like tool calling and planning. Familiarity with agentic development frameworks such as LangChain or AutoGen is necessary. Experience integrating LLMs via APIs or cloud services like Azure OpenAI or AWS Bedrock is essential. Proficiency with vector databases like Pinecone or Chroma, and an understanding of REST APIs and Git are also required. Preferred skills include cloud-native AI services, LLMOps, and experience with development frameworks like FastAPI or Flask.
HCLTech
IT Consulting