CV

Education

• Cornell University, BS in ECE & ME in CS
• Brown University, CS PhD
• Add your years here

Work experience

• Google, AI and Data Systems Research
• Add your roles and dates here
• Add previous experience at startups and large companies

Skills

• Data Systems
• AI Systems & Data Agents
• Data Science
• Software Engineering

Publications

PRISM: Navigating Cost–Accuracy Trade-offs for NL2SQL

Fine-Grained Table Retrieval Through the Lens of Complex Queries.

100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models

Multi-Objective Agentic Rewrites for Unstructured Data Processing.

LLMs and Databases: A Synergistic Approach to Data Utilization.

Is Long Context All You Need? Leveraging LLM’s Extended Context for NL2SQL.

High-Fidelity And Complex Test Data Generation For Real-World SQL Code Generation Services.

Cortex: Workflow-Aware Resource Pooling and Scheduling for Agentic Serving.

CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL.

CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL.

High-Performance Llama 2 Training and Inference with PyTorch/XLA on Cloud TPUs

PyTorch/XLA SPMD: Scale Up Model Training and Serving with Automatic Parallelization

Automated Data Slicing for Model Validation: A Big Data - AI Integration Approach.

Slice Finder: Automated Data Slicing for Model Validation.

Quantifying Uncertainty in Data Exploration.

Democratizing Data Science through Interactive Curation of ML Pipelines.

Automated Data Slicing for Model Validation: A Big data-AI Integration Approach

Unknown Examples & Machine Learning Model Generalization.

Towards Quantifying Uncertainty in Data Analysis & Exploration.

Towards Interactive Curation & Automatic Tuning of ML Pipelines.

Slice Finder: Automated Data Slicing for Model Validation.

Improved Neighborhood Search for Collaborative Filtering.

Towards Quantifying Uncertainty in Data Analysis & Exploration

Estimating the Impact of Unknown Unknowns on Aggregate Query Results.

Unknown examples & machine learning model generalization

Towards Interactive Data Exploration.

A Data Quality Metric (DQM): How to Estimate the Number of Undetected Errors in Data Sets.

Estimating the Impact of Unknown Unknowns on Aggregate Query Results.

A Data Quality Metric (DQM): How to Estimate The Number of Undetected Errors in Data Sets.

Using RDMA for Lock Management.

Towards interactive data exploration

Estimating the Impact of Unknown Unknowns on Aggregate Query Results.

A Behavior Analysis-Based Game Bot Detection Approach Considering Various Play Styles.

Semi-supervised learning for sentiment analysis in mass social media

Distributed Twitter Opinion Mining System Using MongoDB Aggregation Framework

TV program recommendation method using LDA clustering

Sentiment Analysis Using News Comments for Public Opinion Mining

Personalized Expert-Based Recommender System: Training C-SVM for Personalized Expert Identification.

Game bot detection approach based on behavior analysis and consideration of various play styles

BitTorrent Network Traffic Analysis for Peer Link Prediction

Torrent Crawler: a tool for collecting information from BitTorrent networks

Talks

PyTorch/XLA Auto-Sharding

September 18, 2024

Talk at PyTorch Conference, San Francisco, CA, USA

Auto-scaling LLM applications and workloads

July 16, 2024

Talk at Aju University, Suwon, Korea

Large-Scale Distributed Training with Dynamo and PyTorch/XLA SPMD

October 17, 2023

Talk at PyTorch Conference, San Francisco, CA, USA

Identify trends with the Power and Performance API

June 22, 2020

Talk at Apple WWDC, Cupertino, CA, USA

Teaching

Teaching experience 2

Teaching experience 1

Service and leadership

• Add professional service (e.g., PC member, reviewing) and leadership roles here