# About Me




## Shane Zhang (张欣耕)
AI/ML Engineer, LLM Specialist, RAG Expert



## Contact Information
- 732-491-6378
- zhangxingeng970221@gmail.com
- www.shanezhang.com




## Summary
<no value>





## Professional Experience

### Citigroup Inc. US - AI/ML Engineer
*Aug 2024 - Present*

Location: Rutherford, NJ

- Built a fast structured data processing pipeline with Python, reducing processing time from 10 seconds to under 1 second per document, enhancing document handling efficiency by 90%.
- Designed and accelerated a robust RESTful API with Python FastAPI for real-time data ingestion and NLP processing into Postgres SQL database, supporting over 1 million API calls per day.
- Deployed solutions at scale with OpenShift and Apache Spark, streamlining CI/CD procedures with zero downtime over 120 days.
- Leveraged advanced Agentic RAG systems and Knowledge Graphs with RDF and LPG formats using Python and LangChain to improve global retrieval accuracy, increasing the F1 score of AI-driven compliance analysis from 0.32 to 0.71.
- Implemented evaluation metrics and visualizations with LangChain and RAGAS to ensure LLM quality, reducing hallucination rate by 30% and error investigation time by 60%.
- Utilized OpenAI GPT, Claude, and Google Gemini models and fine-tuned open-source LLM models to develop customized and scalable Agentic RAG systems handling over 200,000 API calls per day.
- Developed human-centered evaluation frameworks (RLHF) to assess LLM performance in real-world scenarios, continuously ensuring alignment with user intents for over 2,000 active users.
- Deployed scalable AI-driven RAG systems on AWS, using S3, EC2, Glue, Lambda, SageMaker, and Bedrock for efficient data processing and LLM integration pipelines.
- Developed and deployed FastAPI interfaces and gRPC protocols for efficient API integration across cloud providers like Azure and AWS.

### Robert Wood Johnson University Hospital - AI/ML Engineer
*Jan 2023 - Aug 2024*

Location: New Brunswick, NJ

- Designed, built, and deployed an Agentic RAG system using Python, NumPy, Pandas, JavaScript, SQL, and Chroma vector database, automating the parsing and summarization of over 5,000 research documents.
- Engineered an advanced Agentic RAG system with OpenAI and React framework, reducing onboarding time by 50% and improving research efficiency by 40%.
- Collaborated with a cross-functional team of 15 academic researchers, integrating over 200 feedback points into the NLP system to align the platform with current and future research objectives.
- Conducted monthly workshops on ML usage for 10+ staff members, achieving 80% adoption of ML-enhanced workflow across the organization.
- Utilized AWS SageMaker for model fine-tuning and AWS Bedrock for serving the models in production environments.

### Fiskkit Inc. - Machine Learning Engineer
*Jan 2020 - July 2021*

Location: San Francisco, CA

- Integrated NLP-driven features into the Node.js backend with Python PyTorch (C++ CUDA), enabling real-time text generation and summarization functionalities, cutting response times by 70%.
- Conducted data pre-processing and data exploration using Python PySpark, NumPy, and Pandas, ensuring high-quality data integration and leading to a 20% improvement in model training results using PyTorch distributed.
- Optimized deep learning models through quantization and pruning techniques with TensorRT, achieving a 40% decrease in inference latency.
- Produced a semantic graph database using Neo4j and Cypher queries to store and query complex relationships, improving data retrieval efficiency by 60%.





## Key Projects

### Enterprise-Scale RAG System
*Citigroup*

Built a comprehensive RAG system for financial document analysis using LangChain, pgvector, and AWS Bedrock
Technologies:
- Python
- FastAPI
- LangChain
- Postgres
- pgvector
- AWS Bedrock

### Healthcare Research Assistant
*RWJUH*

Developed an AI assistant for medical researchers using OpenAI APIs, vector databases, and React
Technologies:
- Python
- React
- OpenAI
- Chroma DB
- AWS SageMaker

### NLP Text Analysis Platform
*Fiskkit*

Created an NLP-powered platform for text analysis with Node.js backend and PyTorch models
Technologies:
- Node.js
- Python
- PyTorch
- PySpark
- Neo4j





## Technical Skills

### Generative AI
- LLM Fine-Tuning
- Parameter-Efficient Fine-Tuning (PEFT)
- Retrieval-Augmented Generation (RAG)
- Agentic RAG Systems
- Knowledge Graphs (RDF)
- Knowledge Graphs (LPG formats)
- GraphRAG
- OpenAI GPT
- Google Gemini
- Anthropic Claude
- LangChain
- LangGraph
- Prompt Engineering
- RLHF

### Machine Learning & NLP
- PyTorch
- TensorFlow
- Keras
- Transformers
- HuggingFace
- Natural Language Processing (NLP)
- spaCy
- NLTK
- Feature Engineering
- Statistical Modeling
- Quantization
- Pruning Techniques
- Model Evaluation
- Performance Analysis
- Neural Networks
- GANs
- Stable Diffusion

### Data Engineering
- Postgres with pgvector
- FAISS
- Chroma
- Neo4j
- Cypher
- MySQL
- PostgreSQL
- Oracle
- Elasticsearch
- MongoDB
- PySpark
- Pandas
- NumPy
- Apache Spark
- Hadoop
- ETL Workflows
- Data Processing Pipelines

### Programming
- Python
- FastAPI
- Streamlit
- PyTest
- JavaScript
- Node.js
- React
- Scala
- Java
- C++
- REST API Development
- gRPC
- JWT
- Authentication Systems

### DevOps & MLOps
- Docker
- Kubernetes
- OpenShift
- CI/CD Pipelines
- Development Workflows
- AWS SageMaker
- AWS Bedrock
- AWS S3
- AWS EC2
- AWS Lambda
- AWS Glue
- Azure Cloud Services
- MLflow
- RAGAS

### Professional & Soft Skills
- Technical Communication
- Documentation
- Team Collaboration
- Cross-functional Leadership
- Stakeholder Management
- Client Presentations
- Mentoring
- Training
- Agile Methodologies
- Project Management





## Education

### M.S. in Computer Science, Machine Learning Specialty - Rutgers, The State University of New Jersey
*Dec 2020 - Dec 2022*

GPA: GPA: 3.71

### B.S. in Computer Science - Rutgers, The State University of New Jersey
*Sep 2017 - Sep 2020*







## Languages
- English (Native, Fluent)
- Mandarin (Native, Fluent)





## Certifications

### AWS Certified Machine Learning - Specialty (MLS-C01)
*Amazon Web Services* - Jun 2024

This certification validates expertise in building, training, tuning, and deploying machine learning, Deep Learning, Generative AI, and LLM models on AWS.






## Teaching Experience

### Teaching Assistant - Rutgers University
*Dec 2020 - Dec 2022*

Tutored over 400 students in Computer Science and Machine Learning topics






## Additional Information

### Publications
- Berns, M. P., Nunez, G. M., Zhang, X., et al. (Sep 2024). Auditory Decision-making Deficits After Permanent Noise-induced Hearing Loss.





## Interests
- Generative AI
- SCUBA Diving
- Reading
- Philosophy
- Psychology
- Sociology



---
Resume generated from structured data - Visit the full interactive version at: https://www.shanechang.com/about-me/