Open Source
Core ML Tools — LightGBM to Core ML converter supporting Booster, LGBMClassifier, and LGBMRegressor models.
coremltools Core ML LightGBM
Xijing Wang (Thomas)
Apple Machine Learning Engineer Intern · MLE / MLSys · AI Agent
Carnegie Mellon University, School of Computer Science
I'm a graduate student at Carnegie Mellon University (School of Computer Science), pursuing an M.S. in Automated Science.
I received my B.S. in Computer Science (emphasis in Algorithms) from Santa Clara University, where I worked with Dr. Lang Chen. Dr. Nicholas Q. Tran served as my academic advisor.
My interests lie in on-device ML and LLM inference, ML systems, agentic ML workflows, and full-stack intelligent applications.
Looking for opportunities in On-device ML, MLSys, AI Infrastructure, and AI Agents. Please reach out at xthomaswang@gmail.com.
Updates
Last updated: Jul 2026 Open Source
Selected projects I contribute to or build:
Activity feed
Work
Machine Learning Engineer Intern at Apple (May 11 — Aug 21, 2026), building agentic end-to-end ML training workflows for cellular ML models and developing Call Context, a feature announced at WWDC26, using on-device LLM inference.
Apple Agentic ML Core ML On-device LLM
Publication
Article published in Communications Biology — E/I imbalance and internal noise cause weak neural representations and face recognition challenges in ASD.
Nature Portfolio ASD Computational Neuroscience
Open Source
Open source contributor to apache/tvm — end-to-end deep learning compiler stack for CPUs, GPUs, and specialized accelerators.
TVM Compiler MLSys
Open Source
Building the Localized Agent Harness — a local-first agent harness with progressive long-term memory and Sleep Model embedding fine-tuning. Modular Melo / Support / Test architecture, supporting Ollama, MLC, and OpenAI-compatible backends.
Agent Harness AI Agents Memory
Open Source
Open source contributor to mlc-ai/mlc-llm — on-device LLM deployment framework. Used in Headache Note iOS app with quantized LLaMA 3.
MLC-LLM On-device LLM iOS
Open Source
Open source contributor to xthomaswang/OpenOT2 — lab automation framework for the OT-2 liquid handling robot.
OpenOT2 Lab Automation Robotics
Publication
Poster at GenAI4Health @NeurIPS 2025 — The Second Workshop on GenAI for Health: Potential, Trust, and Policy Compliance. San Diego, CA.
NeurIPS Health AI
Research
Research Engineer at CMU — built AI-powered biomedical literature analysis platform with RAG pipeline and embedding-based semantic search. Fine-tuned Qwen3 0.6B embedding model on multi-GPU, achieving strong benchmark on PMC-Patients PPR task.
CMU RAG Embeddings
Education
Started graduate studies at Carnegie Mellon University in the MSAS program, School of Computer Science. Director's Scholarship recipient.
CMU MSAS
Publication
Poster at CogSci 2025 — 47th Annual Meeting of the Cognitive Science Society. San Francisco, CA.
CogSci Neuroscience
Research
ML Research Intern at LCCN Lab, SCU. Fine-tuned CNNs and Vision Transformers to test neuroscience hypotheses. Built fMRI data processing and representation analysis pipelines.
LCCN fMRI Vision
Scroll to browse earlier updates
Experience
Machine Learning Engineer Intern @ Apple
May 2026 — Aug 2026Cupertino, CA
Built agentic developer workflows for cellular ML model training, evaluation, Core ML packaging, and iPhone performance validation. Developing Call Context, a feature announced at WWDC26, using on-device LLM inference; benchmarking different inference strategies and evaluating performance trade-offs on iPhone.
Research Engineer (AI Agent) @ Carnegie Mellon University
July 2025 — Dec 2025Pittsburgh, PA
Built an AI-powered biomedical literature analysis platform with Quick (<30s) and Deep (<=3min) modes using a RAG pipeline with parallel retrieval from PubMed and MedRxiv. Fine-tuned Qwen3 0.6B embedding model on multi-GPU, achieving strong benchmark results on PMC-Patients PPR task. Poster at NeurIPS 2025 Workshop on GenAI for Health.
ML Engineer Intern @ LCCN Lab, Santa Clara University
June 2024 — Sep 2024Santa Clara, CA
Developed CNN models for neuroscience research and preprocessed fMRI data for HPC workflows. Article published in Communications Biology; poster accepted at CogSci 2025.
Education
Carnegie Mellon University
Aug 2025 — May 2027M.S. in Automated Science
School of Computer Science · Pittsburgh, PA
Director's ScholarshipSanta Clara University
Sep 2021 — Mar 2025B.S. in Computer Science, Minor in Economics
College of Arts and Sciences · Santa Clara, CA
REAL Program ScholarSkills
Languages
Python C++ Swift JavaScript Java Go Scala
AI / ML
PyTorch TensorFlow CoreML LLM MLSys OpenCV NumPy Pandas
Mobile
SwiftUI UIKit React Native Core Data
Backend
FastAPI Node.js Gin (Go) MySQL SQLite
Concepts
MVVM RESTful APIs CI/CD HPC Data Privacy
Projects
Clinical Copilot — Medical Literature Analyzer
ResearchAI-powered literature analysis system using a RAG pipeline with PubMed & MedRxiv. Fine-tuned Qwen3 0.6B embedding model on multi-GPU, achieving strong benchmark on PMC-Patients PPR task. Poster at NeurIPS 2025 Workshop on GenAI for Health.
Python RAG Transformers Qwen3 Multi-GPU FastAPI
apache/tvm — Deep Learning Compiler Stack
Open SourceOpen-source contributor to Apache TVM, an end-to-end deep learning compiler stack for CPUs, GPUs, and specialized accelerators. Focused on operator scheduling and on-device inference paths.
MLSys Compiler C++ Python TVM
Localized Agent Harness — Local-First Agent Runtime
Open SourceA local-first agent harness for always-on agents that automate routine work and learn user habits. Modular architecture (Melo core / Support / Test), with progressive long-term memory and a Sleep Model that fine-tunes the embedding model offline. Hybrid local + API execution, supporting Ollama, MLC, and OpenAI-compatible backends.
AI Agent Local LLM Memory Ollama MLC Python
mlc-ai/mlc-llm — On-Device LLM Deployment
Open SourceContributor to MLC-LLM, an open-source framework for deploying LLMs on-device across platforms (iOS, Android, Web). Used the framework to enable on-device inference with quantized LLaMA 3 models in the Headache Note iOS app.
MLSys LLM C++ Python iOS
OpenOT2 — Open-Source Lab Automation
Open SourceOpen-source contribution to OpenOT2, a lab automation framework for the OT-2 liquid handling robot. Enabling reproducible scientific workflows through programmable protocols.
Python Robotics Automation Lab
Headache Note — Offline iOS AI Agent
SoftwareFully offline iOS AI agent built by quantizing LLaMA 3 1.6B with MLC-LLM, optimized for iPhone. Swift-based health assistant with prompt engineering and SwiftData for private, on-device inference and personalized lifestyle recommendations.
Swift MLC-LLM MLSys PyTorch SwiftUI
Neurocomputational Basis of Face Recognition in ASD
ResearchResearch on face recognition challenges in ASD using CNNs, ResNet50, and Vision Transformers as computational frameworks. Built fMRI data processing pipelines and Pearson correlation analysis. Article published in Communications Biology (Nature Portfolio, 2026); poster at CogSci 2025.
Python TensorFlow Deep Learning Neuroscience HPC
MasumiRanker — AI Agent Platform (Hackathon)
SoftwareAI agent discovery platform with natural language semantic search using Sentence Transformers and Faiss for efficient similarity matching. FastAPI + SQLAlchemy backend with user ratings, recommendation logging, and SHA-256 data integrity.
Python FastAPI Faiss Transformers React
Food Recognition iOS App
SoftwareSwiftUI iOS app with MVVM architecture, integrating a TensorFlow-trained CoreML model for food classification with 85% accuracy across 100+ categories. Optimized inference speed by 4x and reduced memory usage by 40%.
Swift SwiftUI TensorFlow CoreML Python
EmojiAndEmotion — Health Tracking App
SoftwareFull-stack iOS app with React Native and SQLite. Optimized data queries by 75% (200ms to 50ms). Integrated Apple HealthKit for real-time HRV metrics with 98% accuracy. 90% test coverage.
React Native SQLite HealthKit
Social Networking Website
SoftwareFull-stack web server using the Go Gin framework with RESTful API, JSON-based database for efficient data management, and a scalable commenting system.
Go Gin JavaScript HTML/CSS
Resume & CV
Download the version most relevant to you.