Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Hi, I'm Yunpeng Wang, a Data & AI Engineer specializing in building RAG architectures using FAISS, Python, embedding models and agentic workflows. I design semantic search systems with optimized vector databases and production deployments, collaborating across teams to deliver AI-powered infrastructure. I am committed to advancing expertise in multi-agent systems and ML applications, and I enjoy turning complex data problems into scalable, governance-aware solutions.…Hi, I'm Yunpeng Wang, a Data & AI Engineer specializing in building RAG architectures using FAISS, Python, embedding models and agentic workflows. I design semantic search systems with optimized vector databases and production deployments, collaborating across teams to deliver AI-powered infrastructure. I am committed to advancing expertise in multi-agent systems and ML applications, and I enjoy turning complex data problems into scalable, governance-aware solutions.

Yunpeng Wang

Data Scientist, AI Engineer, Full Stack Developer, +2





Hi, I'm Yunpeng Wang, a Data & AI Engineer specializing in building RAG architectures using FAISS, Python, embedding models and agentic workflows. I design semantic search systems with optimized vector databases and production deployments, collaborating across teams to deliver AI-powered infrastructure. I am committed to advancing expertise in multi-agent systems and ML applications, and I enjoy turning complex data problems into scalable, governance-aware solutions.…Hi, I'm Yunpeng Wang, a Data & AI Engineer specializing in building RAG architectures using FAISS, Python, embedding models and agentic workflows. I design semantic search systems with optimized vector databases and production deployments, collaborating across teams to deliver AI-powered infrastructure. I am committed to advancing expertise in multi-agent systems and ML applications, and I enjoy turning complex data problems into scalable, governance-aware solutions.

Available to hire

Hi, I’m Yunpeng Wang, a Data & AI Engineer specializing in building RAG architectures using FAISS, Python, embedding models and agentic workflows. I design semantic search systems with optimized vector databases and production deployments, collaborating across teams to deliver AI-powered infrastructure.

I am committed to advancing expertise in multi-agent systems and ML applications, and I enjoy turning complex data problems into scalable, governance-aware solutions.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Work Experience

Data & AI Engineer at Runwei (Remote, New York)

June 1, 2025 - June 1, 2025

Designed scalable ETL pipelines with Azure Data Factory and Databricks, integrating vector embedding generation into the ingestion workflow to process 60K+ daily records with 12% latency reduction. Developed a RAG-powered chatbot using LangChain, FAISS vector database, LLM API, and BGE embedding models, implementing intelligent chunking strategies and semantic similarity search to deliver context-aware responses for thousands of daily queries with 20% latency reduction and 85% accuracy improvement. Architected optimized SQL schema across Azure Database and Delta Lake with indexing and partitioning, implementing data versioning and governance policies, improving query efficiency by 18% and ensuring GDPR compliance. Designed automated dashboards in Tableau tracking matching success rates, user conversion funnels, and funding pipeline metrics, collaborating with product teams to define KPIs that improved decision-making speed by 30%.

Business Intelligence Engineer | Intern at SALA Holdings LLC

August 31, 2024 - August 31, 2024

Engineered ETL workflows with Airflow and Lambda, automating daily ingestion of 5000+ property listings to AWS S3 and Redshift, reducing manual operations by 25% and implementing data quality validation rules. Built automated reporting dashboards in AWS QuickSight and Tableau, tracking 8 operational metrics for property acquisition workflow and providing real-time insights to stakeholders. Conducted advanced statistical analysis including regression and chi-square tests, identifying market segments with 35% higher retention rates and implementing A/B testing frameworks for targeted marketing strategies. Developed XGBoost price prediction models using Python with feature engineering and cross-validation, achieving 15% accuracy improvement, optimizing portfolio strategy across 9 properties through statistical significance testing.

Data Analyst at Alibaba Youku

June 30, 2022 - June 30, 2022

Built MySQL data pipelines and optimized database schemas for Youku's streaming platform, implementing data governance policies for user privacy compliance, achieving 12% query performance improvement. Developed 10+ interactive Tableau and Power BI dashboards tracking subscription metrics, viewer engagement patterns, and content performance across 100+ categories, providing actionable insights to content and marketing teams. Designed and analyzed A/B testing experiments for subscription conversion and ad placement optimization, contributing to 3% ad revenue increase.