Artificial Intelligence Intern

About the Role

We are looking for a motivated Applied AI Intern with strong Python and problem-solving skills and an interest in building practical AI applications. The ideal candidate should be eager to work with Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), Optical Character Recognition (OCR), and open-source AI models to develop intelligent solutions for real-world problems.

Key Responsibilities

• Develop and maintain AI applications using Python.
• Work with LLMs for text generation, summarization, information extraction, and intelligent automation.
• Build and improve RAG pipelines for document retrieval, semantic search, and question answering.
• Implement OCR solutions to extract structured information from images, scanned documents, and PDFs.
• Explore and integrate open-source LLMs and vision models into AI applications.
• Evaluate model performance and experiment with different models, prompts, and inference strategies.
• Process and transform unstructured data for AI-powered applications.
• Apply Data Structures and Algorithms (DSA) to develop efficient and scalable solutions.
• Integrate AI models and services through REST APIs.
• Debug, test, and optimize AI workflows in collaboration with the engineering team.

Requirements & Tech Stack

• Python: Strong fundamentals, object-oriented programming, exception handling, and familiarity with common Python libraries.
• LLMs: Basic understanding of Large Language Models, prompt engineering, and model APIs.
• RAG: Understanding of embeddings, document chunking, vector search, and retrieval pipelines.
• OCR: Familiarity with extracting text from images and PDFs using OCR tools or libraries.
• Open-Source Models: Basic familiarity with open-source LLMs and vision models, such as Llama, Mistral, Qwen, or DeepSeek, and an interest in using them in practical applications.
• DSA: Understanding of arrays, strings, hash maps, stacks, queues, trees, searching, sorting, and time and space complexity.
• APIs: Basic knowledge of REST APIs, HTTP methods, and JSON.
• Problem-Solving: Strong analytical thinking, debugging, and logical reasoning skills.
• Version Control: Basic familiarity with Git and GitHub.

Good to Have

• Experience with Hugging Face Transformers and model inference.
• Familiarity with LangChain or LangGraph.
• Experience with vector databases such as FAISS, Chroma, or OpenSearch.
• Familiarity with OCR tools such as Tesseract, EasyOCR, PaddleOCR, or other vision-language models.
• Basic knowledge of FastAPI and backend development.
• Exposure to local model deployment or inference tools such as Ollama or vLLM.
• Understanding of machine learning, deep learning, and Natural Language Processing (NLP).
• Academic or personal projects involving LLMs, RAG, OCR, document intelligence, or AI automation.

Qualifications

• Pursuing or recently completed a degree in Computer Science, Information Technology, Artificial Intelligence, or a related field.
• Strong programming fundamentals and a willingness to learn new AI technologies.
• Academic projects, personal projects, or contributions to open-source repositories are an advantage.

What You Will Gain

• Hands-on experience developing real-world AI applications.
• Practical exposure to LLMs, RAG architectures, OCR pipelines, and open-source AI models.
• Experience integrating AI models into Python applications and APIs.
• Opportunities to experiment with model evaluation, inference optimization, and document intelligence.
• Mentorship and experience solving practical engineering challenges.

Ideal Candidate

A curious and technically strong individual with good Python and DSA fundamentals who is enthusiastic about exploring AI technologies and applying them to real-world engineering problems. The candidate should be willing to experiment, learn quickly, and build practical solutions using both open-source models and AI APIs.