Ashish Kushwaha

Currently Building a Full Stack RAG LLM solution for a cyber security Project. Finetuned LLAMA-3.1 model to get threat intel information. Implemented RAG pipelines and used Finetuned models to get accurate and precious real time threat intel data. Built stateful agent orchestration using LangGraph, enabling conditional reasoning, contextual memory, and user-specific responses in production RAG systems. Implemented Redis cache and memory management to store cache and short term memory of llm query response cycle. Implemented Session implementation using Redis to serve users their own request. Built CI-CD pipelines and Deployed in AWS EC2 and implemented LLMOPS concepts.

Modeled RAG workflows as a state graph using LangGraph, enabling deterministic control over multi-step LLM reasoning and tool execution. Implemented Query Transformation Feature to enhance input user query to get accurate retrieved documents. Implemented In-text Citation Documents feature using Prompt Engineering. Implemented Claude3 Haiku model using AWS Bedrock. Developed Data Ingestion Pipeline between AWS S3 Knowledge Base, AWS Kendra and AWS ECS.

Cancer Cells Detection: Gathered a comprehensive dataset of medical images, including histopathological slides, mammograms, or radiological scans. These images are annotated with information about the presence or absence of cancer cells. Chose a suitable deep learning architecture for image classification and detection tasks, such as Convolutional Neural Networks (CNNs). The model's ability to recognize subtle patterns and anomalies is crucial. Conducted rigorous validation and testing to evaluate the model's performance. Calculated essential metrics such as accuracy, sensitivity, specificity, and the area under the Receiver Operating Characteristic (ROC) curve. Deployed the trained deep learning model for practical application, integrated into a healthcare system. This enables real-time or batch analysis of medical images for cancer cell detection.

Waste in the Street Photo Detection: Developed algorithms that could effectively identify and quantify waste in various environments captured in photographs. Utilized a custom CNN model for image classification, capable of identifying and categorizing waste items in street photographs. Created an automated system that processed images and flagged those containing street waste, enabling faster and more efficient waste detection. Potholes in Photo Detection: Developed a computer vision model to detect potholes in photographs, thereby aiding municipal bodies in road maintenance tasks. Created an automated system that streamlines the detection process, reducing the need for manual inspection and speeding up response times. Improved response times for pothole repair by providing an automated system for pothole identification and prioritization. Hyperboles in Radargram Detection: Designed a system that effectively detected hyperbolic patterns in radargram images. Demonstrated proficiency in radar data analysis, including data preprocessing, signal identification, and real-time processing. Trained the deep learning model using a well-annotated dataset, ensuring the model learned to recognize relevant patterns.