Komal Vij
B.S./M.S. Computer Science (AI)
I work on personalization, reinforcement learning, and AI safety, especially learning from sparse feedback.
- Research
- Applied Science
- ML Engineering
- Product Engineering
- Infra
Research Papers & Posters
Automatic accessible presentation generation from IPCC reports. Published at the Tackling Climate Change with Machine Learning workshop.
Reinforcement learning framework using DQN for siRNA sequence optimization.
Multi-agent dialog for synthetic data enhancement for LLM safety.
Projects
- #1 Hackathon Prize · Ecopreneurship Track
ZoneZero
Geospatial environmental analysis tool using Google Earth Engine and Maps data to generate a Zone Zero wildfire-compliance report for any address.
- #1 Place · AGI House Hackathon
MemoryPalace
Biomimetic parametric memory system that improves vision-language model spatial reasoning on long-form egocentric video.
T-REX Preference Learning
Investigating whether Trajectory-ranked Reward Extrapolation (T-REX), an inverse RL technique from robotics and game-playing, can recover latent user preferences for recommendation from implicit signals alone, using a custom simulation environment.
Work
SWE / ML Intern · Uber Eats Personalization
Built Bayesian popularity scoring and the candidate-generation pipeline for carousels serving 100% of traffic; projecting a 3–6% lift in item conversion across 140M+ users.
Full-Stack ML Intern · Uber
Built on-trip audio anomaly detection for rider and driver safety, quantizing the model to under 5MB on-device at 92% accuracy.
Forward Deployed Engineer Intern · Fetch.ai
Built a voice-agent onboarding pipeline that got 40+ businesses live on Agentverse, cutting onboarding time by ~90%.
Speaking
The Investment Horizon
Fireside on emerging trends in AI investing.
HeyBoss AI
Leadership & Extracurriculars
Stanford Women in Computer Science
Lead sponsor partnerships with Google, OpenAI, Uber, HRT, Bloomberg, and more, and have organized 60+ events on campus with partners.
Stanford Entrepreneurship Society (ASES)
Selected into a highly competitive Bootcamp cohort (~8% acceptance) and pitched a startup to a panel of 20 VCs, including the CTO of Dropbox.
Stanford Computer Forum
Represent the Computer Forum, connecting Stanford students and faculty with industry partners.
Bay Area Founders Club
Organized two conferences with 100,000+ attendees and moderated 40+ events and panel interviews.