Senior RPA Developer - Core (IN)
HCLTech
HCLTech
This role focuses on designing, building, and supporting intelligent applications powered by advanced AI technologies like Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG).
You'll work with autonomous agents, agentic AI frameworks, and integrate LLMs with enterprise data sources, APIs, and cloud services. The goal is to contribute to AI assistants, chatbots, knowledge search, document intelligence, and production-ready GenAI features.
Ideal candidates possess strong programming fundamentals and practical experience in GenAI application development. The position is well-suited for professionals with 1-4 years of relevant experience. Entry-level candidates are encouraged to apply if they can showcase significant project work, internships, certifications, or a robust GitHub portfolio demonstrating proficiency in Python and GenAI concepts.
Develop sophisticated GenAI applications using Python, LLM APIs, prompt engineering, and RAG patterns. Construct AI agents capable of complex reasoning, planning, tool usage, and multi-step execution.
Design and implement RAG pipelines involving document ingestion, chunking, embeddings, vector indexing, and semantic search. Integrate GenAI solutions with diverse enterprise data sources, including documents, databases, and APIs.
Create and manage prompt templates, system prompts, and reusable prompt libraries. Implement tool integrations that enable agents to safely interact with APIs and execute workflows. Support model selection and configuration based on specific use case requirements.
Utilize frameworks like LangChain, LangGraph, or AutoGen to build agentic workflows. Develop reusable components for prompt management, retrieval, memory, and monitoring. Perform rigorous testing and evaluation of GenAI outputs for accuracy, reliability, and safety.
Implement foundational Responsible AI and security controls. Support the deployment and integration of GenAI components into various environments. Document prompts, agent flows, and deployment procedures.
A strong command of Python programming, including data structures, APIs, OOP, and debugging, is essential. Hands-on experience with Generative AI, LLMs, prompt engineering, embeddings, and AI application development is required.
Proficiency in RAG architecture, covering document processing, chunking, vectorization, and semantic search, is crucial. Experience or strong project exposure to agentic AI concepts like tool calling, planning, and task decomposition is necessary.
Familiarity with agentic development frameworks such as LangChain, LangGraph, or AutoGen is expected. Experience integrating LLMs via APIs or cloud AI services (e.g., AWS Bedrock, Azure OpenAI) is important.
Working knowledge of vector databases or semantic search platforms (e.g., Pinecone, Chroma) and an understanding of REST APIs and JSON are required. Proficiency with Git, code reviews, and Agile methodologies is also necessary.
Preferred skills include exposure to cloud-native AI services, multi-agent systems, LLMOps/GenAIOps, OCR, and document intelligence. Experience with application development tools like FastAPI or Flask is a plus.
HCLTech
IT Consulting