-
🔭 Current Work Experience:
-
I’m currently working as a Software Engineer @ Capybara.AI
- Engineered a high-concurrency system for real-time financial news collection, analysis, and sentiment scoring, optimizing data flow and prediction accuracy.
- Designed sector-specific clustering algorithms, integrating sentiment analysis to provide actionable insights for industry-wide trend forecasting.
- Developed a back-inference algorithm that identified key drivers of stock price fluctuations, achieving a 73% accuracy rate in matching news to market movements.
-
-
🔬 Current Research Experience:
-
I’m currently working as a Undergraduate Researcher with Ph.D. Ruixuan Zhang @ AI4CE
- Constructued video counting and tracking evaluation pipeline.
- Designed and implemented the model input datasets and streamline the data processing pipeline.
-
-
🔄 Earlier Work Experiences:
-
Software Engineer Intern @ Zilliz
- Integrated Milvus Vector Database with open-source tools to enhance RAG workflows.
- Designed a comprehensive embedding model evaluation framework, to improve RAG performance and streamline future model integrations.
- Built an automated GitHub sourcing agent, retrieving 70+ projects daily.
-
Full-Stack Developer @ Repartee.AI
- Enhanced ElasticSearch-based indexing for technical documents, improving search accuracy and efficiency.
- Built backend functionalities for billing, authorization, and portfolio management using Nest.js and Next.js.
-
Full-Stack Developer @ Ecowise (Hackathon Project)
- Developed an energy-saving chatbot using GPT-3.5 to provide personalized tips and quizzes.
-
-
📫 How to reach me: [email protected]
💪
Working
Computer Science, Math | Junior @ New York University
- New York
-
01:58
(UTC -12:00) - in/haoxuan-jackson-xie-905a79251
Pinned Loading
-
-
SciPhi-AI/R2R
SciPhi-AI/R2R PublicThe most advanced AI retrieval system. Containerized, Retrieval-Augmented Generation (RAG) with a RESTful API.
-
whyhow-ai/rule-based-retrieval
whyhow-ai/rule-based-retrieval PublicThe Rule-based Retrieval package is a Python package that enables you to create and manage Retrieval Augmented Generation (RAG) applications with advanced filtering capabilities. It seamlessly inte…
-
-
zylon-ai/private-gpt
zylon-ai/private-gpt PublicInteract with your documents using the power of GPT, 100% privately, no data leaks
-
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.