Jethro Arciaga
Python and Data Engineer with a strong background building scalable data pipelines, automated web scraping systems, and AWS integrations.
About
Python and Data Engineer with a strong background building scalable data pipelines, automated web scraping systems, and AWS integrations. Experienced in processing unstructured data including advanced PDF extraction and real-time live-video transcription ingestion.
Skilled in modern AI tools (Claude, Promptfoo, MCP servers) to build automated workflows, benchmark prompt logic, and accelerate engineering efficiency. Delivered ETL and API-driven integrations across AWS, Azure Blob Storage, and serverless architectures, with a focus on reliability and test-backed CI/CD.
- 5 years' experience
- Joined July 2026
Industry experience
- Software & Internet
- Professional Services
- Government
- Financial Services
- Media & Entertainment
Work experience· 4 roles
Architected and optimized high-throughput, AI-driven data extraction and ingestion systems on an in-house orchestration platform. Built scalable pipelines for advanced PDF mining/extraction to transform complex documents into structured datasets for downstream analytics. Engineered low-latency real-time live-video ingestion (live transcript) to capture closed-caption metadata and process structured data on the fly. Developed on-demand instant-transcript video extraction using Python and advanced scraping techniques to retrieve, clean, and parse deep text from URL-driven video targets. Implemented intelligent email automation with asynchronous LLM classification using Claude to extract key payloads and categorize message types, along with prompt evaluation using Promptfoo to prevent production regressions.
Developed and maintained the company website (creativejourneysph.com) using modern front-end and backend technologies, ensuring functional updates and reliable deployment workflows.
Created and maintained ETL pipelines for Open Architects, ensuring secure and seamless integration with client data via APIs and/or Selenium. Transformed data into expected formats and stored outputs in Azure Blob Storage. Supported automated processing and reliability through testing practices and CI/CD workflows.
Education
Certifications and awards· 5
Hire Jethro Arciaga today
Post a job and invite Jethro, or contact them directly. No hidden commission.







