Experience.
Carnegie Mellon University
Graduate Research Assistant
Reinforcement learning for foundation models in Prof. Andrea Zanette's group.
Amazon
Software Engineer Intern
AI for Customer Service
Built an ML-gated fraud check for customer damage claims.
moreless
- Architected an ML-gated damage-claim verification feature to block fraud and reduce manual review.
- Engineered a secure image-upload pipeline (S3 + virus scanning) passing scanned images to a computer-vision service that synchronously verifies reported damage and gates approval.
- Built the Java/Kotlin backend orchestrating the multi-step upload-to-decision sequence across services.
Salesforce
Software Engineer Intern
Metadata-Driven Services
Built no-code ML features in Salesforce Data Cloud.
moreless
- Built virtual formula fields in Salesforce Data Cloud for no-code ML features at enterprise scale.
- Implemented query-time computation over data objects, eliminating staleness and storage overhead.
- Engineered the Java/Apache Spark layer for formula evaluation over cross-object joins and aggregations.
Cornell Course Management System
Lead
Led the software engineering team behind Cornell's course management system.
moreless
- Led a team of 20 engineers building Cornell’s course management system, used by 10,000+ students.
- Architected the React/TypeScript student-facing frontend, reducing page load times by 90%.
- Implemented APIs with serializable data structures for secure frontend/backend communication.

Generative AI @ Cornell
Machine Learning Engineer
Founding Member
Built LLM agents and AI tutors.
moreless
- Developed AI agent for QuickFi, a commercial lending technology company, automating insurance certificate validation and compliance verification processes, replacing a manual review step.
- Built frontend and vector database for ClassGPT, enabling professors to create AI tutors for classes.
Carnegie Mellon University
Software Engineer & Research Intern
NSF REU
Built a polymorphic type system for SASyLF, a language for writing proofs.
moreless
- Worked on the interpreter for SASyLF, a language for writing proofs, implementing core features in Java.
- Implemented a polymorphic type system for SASyLF, similar to Java generics, enabling type-safe code reuse and significantly reducing duplication in proofs by allowing abstraction over multiple data types.
Cornell Bowers CIS
Teaching Assistant
- CS 3780/5780Introduction to Machine Learning
- CS 4820/5820Analysis of Algorithms
- CS 3110Data Structures & Functional Programming