Developed and deployed a RAG-based Generative AI wellness chatbot for Alignera, integrating NVIDIA NIM, Groq, and TogetherAI LLMs with multi-provider search capabilities.
Architected and deployed advanced features including contextual pro search, real-time streaming, and automated video summaries, driving user engagement through FastAPI, React, and TypeScript.
Showcased the solution's ROI and technical capabilities to potential clients at Greenbuild Conference 2024, resulting in positive stakeholder feedback on RAG capabilities.
InternJune 2023 - August 2023
Infinite SolutionsRockville, Maryland
Spearheaded automation of member rate code validation through Python scripting, eliminating manual errors and reclaiming 10 hours per week of team productivity.
Utilized Python and Excel to identify and resolve member data discrepancies, collaborating closely with data analysts and operations teams to uncover root causes of inconsistencies, reducing inconsistencies by 30% and improving machine learning model accuracy by 5%.
InternDecember 2022 - January 2022
International Software SystemsGreenbelt, Maryland
Enhanced asset management through IATS software implementation, achieving 100% tracking accuracy and reducing discrepancies by 20%.
Executed comprehensive OS deployment across Windows, Linux-Ubuntu, and Kali platforms, resulting in 25% efficiency improvement through standardized infrastructure.
Optimized enterprise-wide hardware integration, delivering 98% network uptime and 15% performance improvement through strategic domain architecture.
Projects
Fitness Trainer ChatbotOctober 2024
Ashburn, Virginia
Designed an AI fitness chatbot leveraging the Meta Llama 2 model in Pytorch, Integrating RAG architecture with ChromaDB for knowledge retrieval.
Accelerated model performance through PEFT and LoRA techniques, achieving efficient deployment via 4-bit quantization.
Skin Melanoma PredictionMay 2024
College Park, Maryland
Trained a convolutional neural network in Pytorch on a dataset of 10,000 dermoscopic images, incorporating advanced data augmentation and normalization techniques.
Achieved a test accuracy of 90% in identifying melanoma cases, demonstrating the model's potential as a screening tool to aid in early skin cancer detection.
Skills
Programming
PythonJavaHTML/CSSC++C
Tools
IntelliJPyCharmEclipseAWSJupyter NotebooksVisual Studio Code