Assist in designing, developing, and testing AI/ML models and applications.
Build and optimize Retrieval-Augmented Generation (RAG) pipelines using vector databases and embedding models.
Work with Large Language Models (LLMs) through APIs and open-source frameworks.
Perform data collection, preprocessing, cleaning, and feature engineering for AI/ML projects.
Implement prompt engineering techniques to improve the performance and reliability of LLM-based applications.
Integrate AI models with backend services and APIs.
Research and implement the latest advancements in AI, Generative AI, and Machine Learning.
Required Qualifications
Currently pursuing the final semester of a Bachelor's degree or a recent graduate.
Final semester students and recent graduates are highly preferred, as this internship is intended to transition into a full-time position based on performance and successful completion of the internship.
Strong understanding of Machine Learning fundamentals, NLP and Deep Learning concepts.
Understanding of Retrieval-Augmented Generation (RAG) architecture and its components.
Familiarity with Large Language Models (LLMs) such as GPT, Llama, Claude, Gemini, or similar models.
Knowledge of embeddings, vector databases, semantic search, and document retrieval concepts.
Proficiency in Python programming.
Familiarity with libraries such as NumPy, Pandas, Scikit-learn, TensorFlow, or PyTorch.
Basic understanding of REST APIs and AI model integration.
Familiarity with Git and version control.
Strong analytical, problem-solving, and communication skills.
