Rui Wang
Sr. AI Algorithm Engineer
M.Eng. from Arizona State University
About Me
I am an AI and search algorithm engineer who turns research ideas into reliable products. My work spans large language models, retrieval, ranking, recommendation, and data-intensive systems.
I hold a Master of Engineering from Arizona State University. I build RAG and knowledge-base applications, search and ranking systems, and the evaluation and deployment workflows that support them.
Key Expertise Areas
Large Model Development
Document Retrieval
Recommendation Systems
Big Data Processing
Python Programming
MLOps
Skills
Large Model Development
Proficient with LangChain for local Q&A systems, chatbots, knowledge bases, and other RAG applications. Experienced with chains, tool-using agents, and function calling.
Document Retrieval & NLP
Proficient in document search, named entity recognition (NER), and sentiment analysis. Skilled with search engines such as Solr and Elasticsearch, with an understanding of Lucene.
Recommendation Systems
Experienced in developing applications based on recommender systems using common algorithms. Knowledgeable in leveraging large models within recommender systems.
Big Data Processing
Proficient with data tools such as NumPy and Pandas. Experienced with Spark for data cleaning, extraction, analysis, and cluster tuning.
Programming & Frameworks
Proficient in Python and frameworks such as FastAPI and Flask. Familiar with MySQL, ClickHouse, Redis, Linux, and Docker.
Model Deployment & MLOps
Experienced in deploying open-source model services and in distributed training and inference with vLLM, FastChat, and DeepSpeed. Familiar with TensorRT-LLM compilation and Triton deployment.
Data Visualization
Skilled in creating insightful data visualizations and dashboards using tools like Matplotlib, Seaborn, and Tableau to communicate complex data effectively.
Cloud Computing
Experience with major cloud platforms (AWS, Azure, GCP) for deploying and scaling AI applications, including serverless functions and container orchestration.
AI Ethics & Responsible AI
Understanding of AI ethics principles, fairness, accountability, and transparency in AI systems. Committed to developing responsible AI solutions.
Work Experience
Sr. Algorithm Engineer
Shanghai University AI Medical Joint Innovation Research and Development Center (Boai China Enterprise Group)
Jan 2024 - Present
- Developed RAG-related Q&A systems and local knowledge base systems.
- Responsible for data cleaning, fine-tuning, and training of large models.
- Researched and applied the latest technologies in the AI field.
- Conducted local deployment, evaluation, testing, and report generation for open-source large models.
- Researched and deployed distributed inference service architectures for large models.
Sr. Search Algorithm Engineer
LexisNexis
Jun 2017 - Dec 2023
- Conducted development work related to search engine business.
- Trained search reordering models using machine learning (LTR) and optimized search results.
- Developed NLP applications, including tokenizers, NER, and document recommendation.
- Developed data visualization systems and scoring systems.
- Tuned distributed systems such as Solr search engine clusters and Spark clusters.
Sr. Big Data Engineer
Wealink
Apr 2016 - May 2017
- NLP analysis and processing of resume data.
- Debugging data crawlers and designing high-concurrency website architectures.
- Big Data analysis using Spark, report generation, and visualization.
- Developed business logic for resume search using Elasticsearch.
Technology Partner
Hanyou Network
May 2015 - Apr 2016
- Co-founded a mobile game platform project.
- Led the technical department, responsible for R&D of product technical architecture.
- Managed the technical team and overcame technical challenges.
Sr. Python Engineer
Kingnet
Mar 2012 - May 2015
- Developed systems for domestic and international games.
- Debugged and integrated game back-end interfaces.
- Worked on the development of game website frontends.
- Developed and analyzed game log collection systems.
Projects
Large Model Q&A System
Developed RAG Q&A systems and knowledge bases based on open-source large models, fine-tuned for specific industries.
Search Ranking Optimization
Utilized machine learning (Learning to Rank - LTR) methods to train models and Rerank methods to optimize search results, enhancing search experience.
Legal Entity Identification
Performed NER identification for legal entities such as case numbers and company names, trained models, deployed recognition services, and compared results with large model recognition.
User Behavior Analysis System
Processed frontend data with an ELK-inspired architecture and stored it in Elasticsearch and ClickHouse for log analysis at billion-record scale.
Hyperlink Cross-Referencing System
A system that handles cross-referencing of articles and builds links. Analyzes citation relationships among billions of documents and provides relevant recommended articles using NLP.
AI-Powered Content Generation
Developed a tool leveraging generative AI models to assist in creating various types of content, including articles, summaries, and creative text.
GitHub Contributions
Below is a snapshot of my GitHub activity.
Contact
If you are interested in my work or have a collaboration inquiry, please contact me by email.
You can also find me on the following platforms:
Social links will be added soon.