San Francisco Bay Area
I love building things, from systems and tools to ideas that solve challenging problems! I like building projects where I can break down complex constraints, prototype quickly, and iterate until something actually works. Most of my experience is in software engineering, ML-driven systems, and backend infrastructure, but the common thread is simple, I enjoy figuring things out. I’ve worked on research and engineering teams in high-performance computing, security, and machine learning, and I’ve spent a lot of time teaching and mentoring other students. These experiences shape how I approach problems: focus on fundamentals, understand the constraints, and build with intention. I’m always on the lookout for opportunities where I can take ownership of problems end to end, learn from great teammates, and ship work that makes a real impact! If you have an interesting idea, let's chat!
- Built RAG pipeline to generate visual art descriptions for 20K+ artworks using Multimodal LLMs - Developed and implemented evaluation methodology like classification of descriptions to whether they have subjective analysis - Accepted and presented findings at AI in Liberal Arts Symposium at Connecticut College - Gathered insights from 20+ vision-language papers to guide few-shot training
• Co-led the launch of an AI-powered recruiting platform adopted by 160+ candidates by engineering core infrastructure and features in React, Next.js, and Python; managed data using a PostgreSQL database • Boosted candidate-job match accuracy by 50% by implementing vector-similarity based resume ranking • Built & deployed sub-1100ms latency voice assessment agent using Deepgram, OpenAI & Cartesia on AWS Fargate • Ensured 100% database uptime by managing Supabase migrations and deploying secure authentication with Clerk
• Founding member of first-ever startup accelerator at college to assist startups in developing tech and raising capital • Created 10+ software engineering templates for mobile app, web dev, and web scraping, including a working stock trading app