Sunil Rufus Email & Phone Number

California, United States

Sterling, Virginia, United States

Buffalo, New York, United States

Emotional support Chatbot: NLP, Hugging Face, PyTorch, LORA, SFT, and Kafka• Built emotional assistance chatbot by fine-tuning MISTRAL-7B on ExTES dataset using Low Ranked Adaptation (LORA) and Supervised Fine Tuning (SFT) with Hugging Face and PyTorch, reducing trainable parameters by 10,000 times and GPU memory requirement by 300%. • Utilized Bag of Head Nouns and Personal Space Graph to increase the context length, while preserving the content.• Utilized GPT-4 to evaluate responses, achieving Spearman and Pearson coefficient of 0.71 and 0.84 against human scores. Deployed on humanoid robot, reducing transmission time by 30% using Kafka.Author Attribution using Embedding Fusion: ML, PyTorch, LLMs, CNN, LSTM, and Transformers• Leveraged embeddings from GPT, FLAN, Llama and RoBERTa to get the stylometric of writing between AI and Human generated texts using CNN, BiLSTM and Transformer architecture. • Performed embedding fusion of the above embeddings to classify achieving a minimum of 96% accuracy and 93% MCC on Deepfake Text Detection dataset.

New York, United States

Efficient Data Extraction and Retrieval: NLP, Selenium, LangChain, docker and pinecone.• Scraped details of around 100K staff members from 2000+ educational institutions with SELENIUM and preprocessed into a structured format using prompt techniques with GPT-3.5 turbo from OpenAI, resulting around 300% boost in efficiency for targeting clients.• Powered up storage and retrieval pipeline by leveraging LANGCHAIN, integrating PINECONE, an embedding model (instructor-base) to retrieve details, and deployed on DOCKER, contributing to streamlined operations.Web-based Query Resolution Chatbot: GPT, HTML, CSS, Bootstrap, FastAPI• Created a chatbot to answer queries about the company using GPT-3.5 model and integrated it into the company’s website using HTML, CSS, Bootstrap and FastAPI.

Chennai, Tamil Nadu, India

Data Extraction, Search and Retrieval Pipeline: NLP, ML, Haystack, Tabula, Elasticsearch, Azure• Extracted data from pdf using TABULA and preprocessed it into sentences and text files followed by indexing. • Developed a searching mechanism using HAYSTACK to retrieve the answer from embeddings attributing source.• Implemented ELASTICSEARCH as a search engine for indexing and retrieving increasing search efficiency by 60%. • Collaborated with 4+ clients from the construction industry to improve search results and ease of usage. • Azure Blob was used for storage and application was deployed using Azure VM.

Chennai, Tamil Nadu, India

Financial Data Processing with Analytics, Forecasting and Chatbot Integration: Dask, Ray, AWS, Plotly• Engineered a product that processes financial data, displays comparative analyses, visualize data trends, patterns and metrics using plotly. • DASK was employed to preprocess the data and RAY for workload scaling and accelerate computations. • Processed financial data and enhanced forecasting using ARIMA with 95% accuracy, reducing manual effort and retrieval time by 90%, along with addressing data related queries using texts and charts whenever required.• Integrated a chatbot that allows users to query the data and get insights, using spacy and nltk.• Employed FastAPI to craft API calls, AWS EC2 for launching applications, and Amazon S3 for efficient storage.

Hosur, Tamil Nadu, India

• Collected dataset (images) employing RaspberryPi, labeled and trained using SSD Mobilenet for localization, achieving 97% accuracy and Resnet50 to identify the characters on an engine block achieving 85% accuracy• This reduced the manual labor by 75%, automating the process of storing identification numbers on engine. • Launched it on Jetson Nano after converting graph into a TensorRT format.

Master'S Degree, Computer Science

Coursework: Machine Learning, Pattern Recognition, Computer Vision and Image Processing, Data Models Query Language

Bachelor Of Engineering - Be, Computer Science And Engineering