Ayush Ranjan

Ayush Ranjan

Graduate Student At University of California

About Me

Hey, I'm Ayush Ranjan, originally from Madhubani, Bihar, India, a town renowned for its exquisite paintings. I've always been drawn to the world of IT products and services, viewing them as the digital monuments of our age. Much like civil engineers build physical bridges, I aspire to contribute to building the digital bridges that connect our modern world.

I completed my B.Tech. in Information Technology from Manipal University Jaipur. My interest in computer science blossomed as I delved into understanding the intricacies of the Internet. My journey in tech began with creating web and mobile applications.

During my undergraduate years, I became deeply engrossed in Deep Learning. My B.Tech. Project involved using Convolutional Neural Networks (CNN) for sentiment analysis of text, inspired by a paper on Sentiment Analysis using CNN. This experience reinforced my belief that learning algorithms from data is a potent approach to problem-solving.

My focus then shifted towards the software industry and development. I honed my skills during an internship at Capgemini, where I served as a Senior Analyst Intern and Java Full Stack Developer. There, I had the opportunity to lead a team of 6 interns in developing a Medical Portal using Spring Boot for the backend and React for the frontend. I seamlessly integrated the frontend and backend via Axios, enhancing user experience and data security.

Afterward, I received a full-time offer as a Senior Analyst at Capgemini in Mumbai. In this role, I worked on the Mercedes-Benz project XDIS (Cross-platform Data Information System), a crucial tool for vehicle diagnostics and automatic driving scenarios. Leveraging my Java expertise, I enhanced software features, optimized various tools/modules, and introduced innovative ideas recognized within the Mercedes-Benz ecosystem. I proudly achieved 3rd place among 60 competing groups at Innocircle 2022, Mercedes' Internal Innovation forum, showcasing my commitment to innovation.

Subsequently, I was promoted to Associate Consultant in my job. After more than two years of working experience, I decided to pursue specialized knowledge by enrolling in a Master's in Computer Science program at the University of California, Santa Cruz. My journey in the world of technology continues, driven by a passion for innovation and a commitment to contributing to the digital realm.

At UCSC, I dedicated myself to the Applied Machine Learning: Deep Learning course, where I excelled and secured the top position in the Final Project Competition hosted on Kaggle. Also I was deeply engrossed in the field of Neural Computation, aiming to broaden my understanding of neural networks. My focus was on my research project titled "Unveiling Glitches: A Deep Dive into Image Encoding Bugs within CLIP." During this time, I secured an A+ in this course. I also Developed and optimized an LSTM model with ResNet50 for feature extraction using an encoder-decoder architecture for image captioning, integrated attention mechanisms, conducted extensive experiments with custom data splits and benchmarks, and addressed validation loss, securing an A+ grade in Advanced Computer Vision course at UCSC.

In addition, I further expanded my knowledge in databases by enrolling in the Design and Implementation of Database Systems course. My goal was to develop a comprehensive understanding of database management principles. Simultaneously, I actively engaged in learning about vector databases, particularly pgvector. I worked towards enhancing the capabilities of vector databases by facilitating the diversification of response sets, implementing dissimilarity constraints, and enabling the low-level composition of multiple queries as a course project, which earned me an A grade.

I am currently serving as an AI Research Assistant under the guidance of Yi Zhang, focusing on advancing AI capabilities in agent capacity, agentic workflows, and web agents. My research investigates how these AI tools can autonomously improve task completion. Prior to this role, I contributed as a Teaching Assistant, mentoring student groups in Agile software projects for CSE-115A Introduction to Software Engineering. Additionally, I facilitated the development of database applications and led discussions on relational and non-relational data models, SQL, and Python forCSE-182 Introduction to Database Management Systems.

Apart from studies, I'm a big fan of football (soccer), both as a player and a spectator. I find pure joy in the game. Beyond the football field, I'm an avid reader, especially when it comes to non-fiction books about technology and its impact on our world. I'm also deeply inspired by the Indian epics, the Mahabharata and the Ramayana, which I believe hold timeless wisdom and captivating tales. When I'm not chasing a football or immersed in a good book, you can often spot me on cooking something delicious.

Key Projects

Unveiling Glitches: A Deep Dive into Image Encoding Bugs within CLIPAI

Recieved A+ in CSE 290D Neural Computation at UCSC for this project.

project name
  • The research project focuses on uncovering glitches in image encoding within CLIP, a model known for its integration of vision and language processing. By employing methodologies like the Discrepancy Analysis Framework (DAF) and the Transformative Caption Analysis for CLIP (TCAC), the study aims to evaluate CLIP's performance and identify areas for improvement.
  • The Discrepancy Analysis Framework (DAF) method is a systematic approach used to evaluate CLIP's performance by comparing its image similarity rankings with those of the DINOv2 model.
  • The Transformative Caption Analysis for CLIP (TCAC) method is an extension of the Discrepancy Analysis Framework (DAF) that focuses on evaluating CLIP's response to image transformations. This approach involves setting up various transformations to simulate real-world conditions, predicting caption probabilities before and after transformations, and manually inspecting images and captions for discrepancies.
  • Through systematic analysis, we reveal discrepancies in CLIP's interpretation of images compared to human perception, highlighting 14 systemic faults, including 4 novel faults.
  • By addressing these limitations, the study lays the groundwork for the development of more accurate image embedding models in artificial intelligence.
  • You can refer to this ppt or github repository to understand more.
You can read the research paper here

Sentiment Analysis With CNN AI

Recieved A+ ( 10/10 ) as my minor Project in my undergrad at Manipal

Supervised by: Shashank Sharma

project name
  • The project is based on implementing Convolutional Neural Networks (CNN) for sentence classification, inspired by the paper "Convolutional Neural Networks for Sentence Classification" presented at EMNLP 2014. The aim is to extract features from text using different filter sizes and numbers to learn various n-gram features.
  • The project utilizes the Spacy library for various NLP tasks such as tokenization, lemmatization, part-of-speech tagging, entity recognition, and dependency parsing. The CNN architecture is designed with multiple convolutional layers of different filter sizes (2, 3, 4, and 5) to capture bi-gram, tri-gram, 4-gram, and 5-gram features respectively. Dropout regularization is applied to prevent overfitting.
  • The dataset is split into training, validation, and test sets, with the vocabulary size limited to 50,002 words, including special tokens for padding and unknown words. Each word is represented using one-hot encoding and passed through an embedding layer to convert them into word embeddings.
  • The forward method of the model involves passing the text data through the embedding layer, followed by separate convolutional layers for each filter size. After applying the convolutional layers, the output tensor is passed through ReLU activation to introduce non-linearity. The resulting feature maps are then concatenated and passed through a linear layer for sentiment prediction. The model is trained using the Adam optimizer and BCEWithLogitsLos function, which combines sigmoid activation and binary cross-entropy loss. The initial representations of word embeddings are obtained from pre-trained GloVe embeddings.
  • After training the model for just 5 epochs, it achieves a test accuracy of 87%, a validation accuracy of 89%, and a training accuracy of 88%. Overall, the project demonstrates the effectiveness of CNNs in text classification tasks using Pytorch.
More about this Project
project name

Enhancing Image Captioning with Attention MechanismsComputer Vision NLPDeep Learning

  • Developed and implemented a baseline LSTM model with Resnet50 for feature extraction using an encoder-decoder architecture.
  • Integrated attention mechanisms to enhance the model's performance, achieving significant improvements with minimal training epochs.
  • Conducted extensive experiments, including custom data splits and benchmarks, evaluated using BLEU metrics.
  • Addressed and analyzed irregular validation loss, exploring learning rate schedules and comparing results with existing implementations.
  • Proposed future investigations into larger datasets and beam search strategies to improve inference.
  • Completed this project as part of my Advanced Computer Vision course, securing an A+ grade.

View on Github

project name

Video to Mp3 Converter Microservice Software Enginnering

  • Developed a microservices-based system with four services, including an authentication gateway, authorization service, video upload service, and converter service. The gateway authenticates users via an authorization service, generating JWT tokens for valid users, enabling secure video uploads. Video-to-MP3 conversion was facilitated using the Python library ”moviepy”.
  • Implemented asynchronous communication using RabbitMQ queues to facilitate seamless video processing and conversion to MP3, ensuring efficient task distribution among services.
  • Utilized MongoDB with GridFS for efficient storage and retrieval of large video files, overcoming MongoDB's 16MB size limit.
  • Managed video and audio file storage, handling, and conversion while ensuring data integrity and secure storage mechanisms.
  • Utilized Docker for containerization, Kubernetes for orchestration, and Minikube for local development, ensuring consistent and scalable deployment across environments.

View on Github

project name

Covid-19 Detection from CT-Scan Deep Learning

I applied 4 layered CNN architecture using Keras on CT dataset of just 350 Ct-Images of 219 peoples to identify covid and non covid patients used 4 convolutional layer followed by Max-pooling. To calculate loss, I used binary cross-entropy. Used data augmentation and dropout to tackle overfitting. Got an training accuracy of 78.9% and test accuracy of 67.3% on such a small set of data.

View on Github

project name

Facial Attendance System AI Software Enginnering

Supervised by: Ginika Mahajan

Utilizing OpenCV, the system captures image frames and employs Haar features and Cascade Classifiers to detect faces within them. Identified faces are then compared against a database for identification. Attendance records of recognized individuals, including date and time stamps, are logged, with the capability to retrieve historical data using names.

The GUI, built with Tkinter, encompasses attendance features and admin query capabilities for login times. Integration of Google Text-to-Speech enhances user interaction with personalized welcome messages for recognized individuals.

View on Github

project name

Personal Website using React Software Engineering

Designed and developed a personal website using React , Bootstrap, JavaScript, HTML and CSS. Deployed the website using Github Pages.

View on Github

Visit the Site

project name

Avoid-Obstacle Game Algorithm Design

Developed a Python(Pygame)-based interactive game featuring character movement control for left and right directions, allowing players to navigate and evade dynamically changing obstacle blocks. The game's challenge dynamically escalates as the speed of the blocks doubles with each successful evasion, providing an engaging and progressively challenging gaming experience.

View on Github

Work Experience

University of California, Santa Cruz

AI Research Assistant - University of California, Santa Cruz

(July 2024 – Present)
  • Conducting research under the supervision of Professor Yi Zhang focusing on advancing AI capabilities in agent capacity, agentic workflows, and web agents.
  • Exploring how these AI tools can autonomously improve task completion.

Teaching Assistant for CSE-182 Introduction to Database Management Systems

(April 2024 - June 2024)

  • Assisted students in understanding database management principles, including SQL, normalization, and indexing.
  • Guided students in developing database schemas, writing queries, and optimizing database performance.
  • Conducted weekly office hours and lab sections to address student queries and provide additional support.

Teaching Assistant for CSE-115A Introduction to Software Engineering

(Jan 2024 - March 2024)

  • Mentored and guided five groups, each consisting of five individuals, through software engineering projects.
  • Conducted weekly progress-tracking calls, offering personalized support and guidance as needed.
  • Provided assistance in project design, emphasizing agile methodologies and collaborative work environments.
  • Cultivated a conducive atmosphere for teamwork and instilled principles of agile methodologies.
  • Adapted teaching methods to diverse learning styles, fostering the development of leadership, communication, and problem-solving skills.

Capgemini Technology Services India Limited - Mumbai

Associate Consultant

(Oct 2022 - Aug 2023)

  • Worked as a Java Developer under Mercedes-Benz Research & Development India. Designed, implemented, and maintained Java features, employing design patterns while performing code reviews.
  • Implemented micro frontend architecture to complement the existing process, enabling users to autonomously modify their vehicle network topology. This approach empowers network experts to review changes independently, eliminating previous dependencies. Resulting in significantly improved efficiency and user experience. This idea got 3rd place among 60 groups for Innocircle 2022, a Mercedes Internal Innovation forum.
  • Worked on innovative concepts to optimize project efficiency, leading to a remarkable 40% reduction in export testing time.

Senior Analyst

(July 2021 - Sep 2022)

  • Initially, worked as a Java Full Stack Developer on the 'Arek Oy' project, a Finnish company, on the development of banking system. This project primarily focused on frontend development and utilized a tech stack comprising React, Spring Boot, Redux, and GitLab for version control. It followed a Maven project structure, with a MySQL database as the data repository. Responsibilities included frontend development, tech stack integration, and codebase maintenance.
  • Later, transitioned to a Java Developer role at Mercedes-Benz Research & Development India's Project XDIS (Cross-platform Data Information System), a critical tool for vehicle diagnostics and automatic driving scenarios in Mercedes. Conducted comprehensive software analysis, programming, and proficiently handled testing and debugging. Contributed to creating well-designed, efficient, and testable code that contributed to project success.
  • XDIS is a core Java program with a swing-based user interface, integrated within the vehicle to download diagnostic data as well as to assist users to change the network topology of their cars. It followed a gradle project structure, with a IBM Db2 database as the data repository.
  • Dramatically optimized XML file migration time by an impressive 66.67%. Additionally, enhanced the tool's robustness by concurrently implementing indexing strategies for associated database tables.

Senior Analyst Intern - Capgemini Technology Services India Limited - Pune

(Jan 2021 - May 2021)

  • Worked as a Java Full Stack Developer, collaboratively engaging in both frontend and backend development.
  • Utilized React for frontend development and Java Spring Boot for backend tasks.
  • Key project involved the creation of an online medical portal, catering to four distinct user roles: User, Doctor, Nurse, and Admin.
  • Ensured thorough documentation for this innovative digital solution.
  • Seamlessly integrated the frontend and backend via Axios, enhancing user experience and data security.
  • Rigorous testing procedures were executed, employing JUnit for the backend and Jasmine for the frontend.

My GitHub Activity