Puranjan B. - Internship - GenerativeAI

Erlangen, Germany

Experience

Nov 2024 - Apr 2025

6 months

Hanover, Germany

Experimented with Generative AI to generate tire patterns based on different customer requirements
Gathered tire images and their feature descriptions
Cleaned dataset of image metadata using pandas
Stored image feature embeddings in Chroma vector db
Used image augmentations to increase dataset size
Used sklearn to create shuffled datasets and imbalanced-learn to balance class sizes in dataset
Used PyTorch to train and test different neural networks to predict tire image from image feature parameters
Validated model using custom accuracy metric based on similarity search in ChromaDB
Visualized accuracy predictions using matplotlib
Plugged in trained model to DreamBooth to train a stable diffusion model and generate new images of tires
Created custom Docker image in Amazon Elastic Container Registry for machine learning script

May 2017 - Nov 2020

3 years 7 months

Bengaluru, India

Completed several projects independently, collaborating with cross functional international client teams (DOW Chemicals)
Implemented end-to-end SAP PO integrations supporting chemical plant order processing and associated financial transactions with banking systems

Proficient in Python, with experience in data analytics and deep learning using PyTorch.
Strong foundation in machine learning and deep learning, including advanced topics such as transformers, diffusion models, and their application in large language models (LLMs). Relevant coursework: Advanced Deep Learning, Explainable Machine Learning.
Hands-on experience in Generative AI through a 6-month internship at Continental.
Applied Generative AI in a project to build an AI coding assistant using LLaMA-based LLMs with Retrieval-Augmented Generation (RAG), leveraging LlamaIndex, LlamaParse, and Ollama.