t
trantienvan

Tran Tien Van

@trantienvan

AI Engineer, Data Engineer and Web Scraping Specialist

Vietnam
Inglese, Vietnamita
Alcune informazioni sono riportate in lingua inglese.
Chi sono
AI Engineer and Data Engineer with 6+ years building production AI agents, LLM apps (GPT-4, Claude, Gemini), RAG, and multi-agent systems with LangChain, LangGraph and MCP. I design ETL/ELT data pipelines, data warehouses (BigQuery, Snowflake) and large-scale web scraping (Python, Scrapy, Selenium, Playwright, proxies, anti-bot). Founder of Van Data Team; shipped 20+ production AI products on AWS, GCP and Azure with FastAPI, Docker and CI/CD. Top 1% on Upwork: Top Rated Plus, 100% Job Success, 5.0 rating across 71 reviews. Let's build something great together.... Continua a leggere

Competenze

t
trantienvan
Tran Tien Van
offline • 

Consulta i miei servizi

Integrazioni IA
I will build a custom ai agent with langgraph and API integrations
A partire da150 USD / progettoMaggiori dettagli
Gestione del cloud
I will audit and optimize your AWS, gcp or azure cloud costs
A partire da150 USD / progettoMaggiori dettagli

Portfolio

Esperienza lavorativa

Upwork

Freelance AI & Data Engineer, Top 1% on Upwork

Upwork

Dec 2020 - Present • 5 yrs 8 mos

Top 1% freelancer on Upwork (Top Rated Plus, 100% Job Success Score) with a perfect 5.0/5.0 rating across 71 public client reviews. Completed 90+ contracts over 2,000+ tracked hours for international clients. - Engineered large-scale web scraping and data extraction systems in Python (BeautifulSoup, Selenium, Playwright) and Node.js (Puppeteer, Cheerio): browser automation with rotating proxies (Bright Data, SmartProxy), CAPTCHA solving (2Captcha), authenticated-session handling, systematic retries, and data validation. - Designed and implemented end-to-end data warehouse and ETL architecture on GCP (Cloud Storage, BigQuery, Cloud Run, Looker Studio) and Snowflake: scalable data models, ingestion and transformation pipelines, and stakeholder dashboards. - Delivered a generative-AI content pipeline on Cloud Run and Cloud Scheduler: Milvus vector database, GPT-4 with text-embedding-3-large embeddings, FastAPI services, and Dockerized deployment with GitHub Actions CI/CD.