Available for contract & full-time remote
Data Engineer & AI Developer
5+ years building production-grade batch and streaming pipelines on GCP and AWS. Delivered data systems for Walmart, Macy's, and BlueCross BlueShield. Google Professional Data Engineer certified.
Selected Work
Production-oriented pipelines built with modern open-source tooling.
Local lakehouse architecture using Airflow, dbt, DuckDB, and Apache Iceberg to support reproducible healthcare analytics and versioned datasets. Synthea generates synthetic patient records; MinIO provides S3-compatible object storage; Nessie handles catalog versioning. Modular DAGs enable schema evolution, data validation, and analytics-ready outputs.
Modular multi-agent orchestration framework built with LangChain. A coordinator agent delegates tasks to specialized sub-agents: a research agent for web summarization, a SQL agent for natural-language-to-query execution, and a RAG pipeline over local documents using FAISS. Structured extraction from unstructured text via Pydantic models.
Contract Work
Available for short-term engagements and project-based contracts. Reach out to discuss scope and rates.
Batch and streaming ETL/ELT pipelines from ingestion to analytics-ready outputs. Airflow, Flink, Kafka, dbt, Apache Iceberg.
Data infrastructure design and migration on GCP and AWS. BigQuery optimization, Lakehouse architecture, cost-effective storage strategy.
LLM-powered automation using LangChain and multi-agent patterns. RAG pipelines, SQL agents, structured extraction, and workflow orchestration.
Schema design, data validation frameworks, and dbt modeling. Audit SQL, fix data integrity issues, and build stakeholder-ready outputs.
Training and evaluation dataset production for ML models — schema consistency, edge case coverage, labeling accuracy, and annotation QA.
Have a project in mind? Available for contracts, consulting, and remote full-time roles.
Start a conversationBackground
I'm Jeremy Tran, a data engineer and AI developer based in Irvine, CA, with 5+ years of experience delivering production data systems at scale. I've worked across the stack at Tredence (Walmart), Infosys (Macy's, BlueCross BlueShield), and as an independent AI/ML data contractor — with a consistent focus on data quality, schema evolution, and analytics-ready outputs.
I hold a BA in Neuroscience from Pomona College and am Google Professional Data Engineer certified. Currently open to remote contract and full-time roles in data engineering and AI.
Languages
Pipelines & Orchestration
Data & Storage
Cloud & Infra
AI & Tooling