Data Engineer · AI

Zhige Wu

I build lakehouses & LLM agents.

View work
Portrait of Zhige Wu
Scroll

Story

Every pipeline is audit evidence.

I started my career auditing listed companies — checking other people’s data. Then I co-founded a startup to fix the tools auditors use. Today I build the data platforms underneath, and the AI that runs on them.

  1. 2019 · Auditor

    Audited 8 listed companies and 6 cross-border M&A deals.

  2. 2022 · Founder

    Built an audit SaaS from zero; automated 70% of manual SOPs.

  3. 2025 · Data Engineer

    Databricks lakehouses, dbt, CDC and multi-cloud log platforms.

  4. Next · AI

    LLM agents on governed, trustworthy data.

Selected work

Experience

  1. 2026Data Engineer (Freelance) · Data Insight ConsultingHamburg
  2. 2025 – 2026Data Engineer · Siyuan Digital IntelligenceHamburg
  3. 2022 – 2025Co-founder & Digital Transformation Manager · Yueyan Creative CultureShenzhen
  4. 2019 – 2022Accounting Analyst & Auditor · Dahua CPABeijing

LanguagesEnglish C1 · Chinese Native

Certifications
  • Azure Data Engineer Associate (DP-203) · 2025
  • Databricks Fundamentals · 2025
  • Azure Administrator Associate (AZ-104)In progress

Writing

  1. Front view of a white phoropter, two mirrored banks of lens dials, each opening ringed by scales and metal knobs, against a light grey background

    AI × DataDeep dive10 min

    Make the analytics agent pass an exam first: inside Data Culture's evaluation framework for dbt

    Data Culture took an e-commerce analytics agent from 0% to 94.7% accuracy without changing the model, by adding context one layer at a time and grading it on a fixed exam. Using their open-source agent-trust-for-dbt repository, I draw the architecture as five layers, from the dbt foundation and the contract the agent reads to a grading cascade that ends in an LLM judge, and sort what you can copy as-is from what you should change.

  2. Over-the-shoulder view of a small aircraft cockpit, two pilots with four-stripe and three-stripe gold epaulettes, one hand on the throttle lever between them, a row of round gauges and two screens ahead

    AI ToolsShort take4 min

    One change through an Entire Trail: where agents step in, where people decide

    Entire, the company former GitHub CEO Thomas Dohmke started, launched a Git forge for people and agents on October 26. It swaps the pull request for a Trail, where review agents rescore every push and gates, CI and people decide whether a change merges. I walked one change through it using the official docs and mapped who does what at each step.

  3. A pegboard wall seen head-on, filled with hundreds of sewing thread cones, roughly grouped by colour into blocks of orange and red, blue and white, beige and brown

    Data EngineeringShort take3 min

    Liquid Clustering "wins three of four workloads", but only three were measured

    An InfoQ benchmark compares partitioning, ZOrder and Liquid Clustering on 50 million Delta Lake rows. I chart latency and data read for the three measured query types, point out that the fourth, a full-scan aggregation, repeats the second one's numbers, and lay out each layout's strengths and weak spots in one table.

All writing

Let’s build something trustworthy.

Open to remote roles and relocation.

Email meLinkedInGitHub