Generative AI Engineer Intern – ABC Company

Role Overview

Work on building and deploying Generative AI applications using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and AI automation to solve real-world business problems.

Key Responsibilities

• Develop and integrate LLM-powered applications using APIs such as OpenAI, Gemini, and Groq.

• Build RAG pipelines using vector databases, embeddings, and semantic search.

• Develop AI agents and automated workflows using frameworks such as LangChain and LangGraph.

• Perform prompt engineering, model evaluation, and output quality testing using LLM-as-a-Judge and evaluation frameworks.

• Work with APIs, Python, and backend frameworks to integrate AI solutions into applications.

• Deploy AI applications using platforms such as Hugging Face Spaces, Vercel, or cloud services.

• Collaborate with cross-functional teams to identify use cases and improve AI application performance.

Required Skills

• Python programming and API integration.

• Understanding of LLMs, prompt engineering, embeddings, and RAG.

• Familiarity with LangChain, LangGraph, and vector databases such as ChromaDB.

• Knowledge of Git, REST APIs, and application deployment.

• Strong problem-solving, analytical, and debugging skills.

Learning Opportunities

Gain hands-on experience in building production-ready GenAI applications, AI agents, RAG systems, model evaluation, and end-to-end AI solution development.