Kailash Shankar
Building
technology
that matters.
University of Florida · CS + Linguistics · GPA 4.0
EDU Africa
Cape Town, South AfricaWorking with a non-profit in Cape Town, I built an interactive mapping application giving residents of underprivileged neighborhoods direct access to local government contacts and a channel to report critical housing issues — from evictions to power outages and water shortages. Every pin on that map represents a family that now has a voice. Built on a MERN stack with a custom REST API, the platform serves 100+ monthly active users across 30+ informal settlements in the Western Cape.
UF GatorAI Club
Gainesville, FLBuilt an AI Teaching Assistant that deploys course-specific chatbot instances for 50+ students, with Gemini 2.0 orchestration and custom guardrails that cut hallucination rates by 30% while maintaining academic integrity. Engineered a RAG pipeline with ChromaDB achieving sub-500ms semantic retrieval across 1,000+ academic documents.
Aug 2025 – Present · University of Florida · with Dr. Zoey Liu
Computational Linguistics Lab
Language shapes how we see the world — yet most of today’s AI speaks only a handful of them fluently. Working with Dr. Zoey Liu, I investigate how data partitioning strategies on LLM training data impact model generalization across the world’s linguistic diversity, with a particular focus on low-resource languages that are systematically underrepresented in modern AI.
My current work quantifies a fundamental trade-off: how much does annotation quality matter when data is scarce? By systematically injecting controlled annotation noise into training sets and benchmarking OLMo-2 across 2,000 languages on UF’s HiPerGator supercomputer, I’m building an empirical map of where AI breaks down — and how to fix it.
Quality vs. Quantity
Modeling the trade-off between dataset scale and annotation fidelity — a question with outsized implications for languages where data is precious.
2,000 Languages
Benchmarking across a typologically diverse language set to understand how multilingual scale affects cross-linguistic transfer beyond high-resource clusters.
Morphological Segmentation
Investigating cross-lingual partitioning of morphologically segmented data across language families to improve zero-shot performance for understudied tongues.
Real problems.
Real solutions.
I'm looking for opportunities where I can keep doing what I love — building technology that has a genuine impact on real people's lives.