Skip to content
View jinhonglin-ryan's full-sized avatar
6 followers · 6 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report jinhonglin-ryan

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
jinhonglin-ryan/README.md

Hi 👋, I'm Jinhong (Ryan) Lin

AI Enthusiast | Software Engineer | CS & Applied Math Junior @ JHU

jinhonglin-ryan

  • 🔭 I’m currently working as a Software Engineer Intern @ Zilliz

    • Integrated Milvus Vector Database with open-source tools to enhance RAG workflows.

  • 🔭 Previously, I was a Machine Learning Engineer Intern @ Pinduoduo

    • Enhanced mContriever models for AI-powered shopping assistants, achieving a +27% recall and +21% F1 score.
    • Developed embedding pipelines and optimized RAG generation, reducing latency by 7.6%.

  • 🔭 Earlier Experiences:

    • Software Engineer Intern @ Capybara.AI

      • Built a concurrent system for real-time news collection, analysis, and sentiment scoring.
      • Designed industry-specific clustering algorithms and engineered tools for financial analysis, integrating sentiment analysis into sector-wide predictions.

    • Multimodal Machine Learning Engineer Intern @ Vipshop

      • Fine-tuned VisualGLM’s Q-Former with advanced attention masking techniques, reducing attribute mismatches by 6.79%.

    • Full-Stack Developer @ Ecowise (Hackathon Project)

      • Developed an energy-saving chatbot using GPT-3.5 to provide personalized tips and quizzes.

  • 🌱 I’m currently learning Machine Learning (Stanford CS229)

  • 📫 How to reach me: [email protected]

Connect with me:

jinhong lin

Languages and Tools:

aws azure bash blender bootstrap c cplusplus css3 django docker elasticsearch firebase flask gcp git go graphql html5 java javascript jest linux matlab mongodb mysql nestjs nodejs opencv oracle pandas python pytorch react redis scikit_learn seaborn selenium spring tensorflow typescript vuejs

jinhonglin-ryan

 jinhonglin-ryan

jinhonglin-ryan

Pinned Loading

  1. leetcode-practcie leetcode-practcie Public

    Collection of LeetCode questions and solutions

    Python 1

  2. web-dev-ecowise web-dev-ecowise Public

    JavaScript

  3. bootcamp bootcamp Public

    Forked from milvus-io/bootcamp

    Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.

    HTML 1

  4. dynamiq dynamiq Public

    Forked from dynamiq-ai/dynamiq

    Dynamiq is an orchestration framework for agentic AI and LLM applications

    Python 1

  5. mcontriever_finetune_training.md mcontriever_finetune_training.md
    1 
    # Fine-Tuning mContriever and Implementing a Retrieval Pipeline for Product Recommendations
    2 
    
              
    
              
    
                3
                
    The integration of artificial intelligence into e-commerce has revolutionized how users interact with products. A cornerstone of this advancement is the ability to retrieve relevant product information efficiently and accurately. In this essay, I discuss the process of fine-tuning the mContriever model and implementing a retrieval pipeline to enhance the performance of an AI-powered shopping assistant. The project’s objective was to improve recall and accuracy while accelerating the system’s overall response time.
    
              
    
              
    
                4
                
    
              
    
              
    
                5
                
    ## Fine-Tuning mContriever
    
              
    
          
    
    
    
  
    

    6. 

      
  6. 
  
    
    
    
      
    
        
    
            
          
pairwise-trading-strategy
pairwise-trading-strategy          Public
        
    
      
    


      
    
        
      
    

      
    
          
  
  Python


      
    
    
    
  
    

    7.