San Francisco Bay Area
Hi there! I'm Harsh, a: Hacker. Tinkerer. Changemaker. I'm an entrepreneur at heart but I enjoy diving into the world of computer science and solving complex problems. My passions lay in backend and infrastructure development, cybersecurity, quantitative trading, and applied AI. I recently graduated from UC Davis with a bachelor’s degree in computer science with an emphasis in operating systems, AI, and networks. I be continuing my studies at UIUC and working towards a Masters in Computer Science with a concentration in AI/ML infrastructure and am a part of several campus initiatives where I am working on the intersection of my passions. Outside of my academic and professional life, I have also recently discovered newfound passions for basketball, game theory, and chess. I am always willing to explore new opportunities and have a quick chat!
- Building AI agents to support critical path of Google Cloud, infra, and database teams - Agent evals, orchestration, memory management, and agentic workflows
- Prediction Markets - Market Making Infrastructure - Crypto Transfers
• Researching LLM memory behavior and data persistence under guidance from Prof. Zubair Shafiq, with a focus on developing first-of-its-kind benchmarks for data persistence, involuntary personalization, safe forgetting, and long-term memory evaluation • Conducting research into memory of LLMs to identify lapses in data deletion, involuntary personalization, vulnerabilities, and commercial memory controls in C++ and Python from dataset of 200,000 conversations • Previously led analysis of agentic computer use tools, using MITMproxy, HAR logs, and custom network scrapers to uncover hidden data flows and privacy risks • Collaborating on tools and metrics that quantify model forgetfulness, hidden personalization drift, and residual exposure, contributing to the development of safer, more controllable foundation models
• Focused on code security, cryptocurrency and blockchain infrastructure and augmenting manual code reviews of 1 million+ lines of code using C++, Python, Go, and Rust and testing with PyTest • Creating custom abstract syntax trees + RAG system to represent syntactic structure of code and using machine learning for fuzzy matching with consensus layer specs to identify vulnerabilities 80% faster
• Developing a web-based AI assistant for behavioral and technical interview prep, using Next.js, TypeScript, and Supabase • Integrated Hume AI’s computer vision models to detect facial expressions and emotional shifts in real time, generating personalized feedback on delivery, tone, and clarity • Building LLM-based question generation and feedback flows using Mistral and prompt engineering to simulate interviewer behavior • Deployed application on Modal, with scalable back-end APIs and secure session management for multi-user interviews