Define the right problem
Enter the real workflow and find the bottleneck that changes outcomes instead of forcing a model-first idea.
Available for AI delivery projects
I’m wude. I build Java backends and AI applications, and lead engineering teams. From discovery and architecture to critical-path implementation and production launch, I connect requirements, data, models and systems into a complete delivery process.
SERVICES
What I deliver
FROM FIELD TO PRODUCTION
DISCOVERY & STRATEGY
For teams that see AI potential but do not know what to build first. Find the highest-value entry point before committing to development.
PROTOTYPE & VALIDATE
For projects that need to reduce uncertainty. Test the workflow, quality and adoption with real data before making the full investment.
INTEGRATE & DEPLOY
For teams with a demo stuck before launch. Connect the solution to existing data, permissions and business systems, then make it maintainable.
ADOPT & ITERATE
For systems already live but not yet reliable in use. Improve them around real feedback and transfer the capability back to the team.
CAPABILITIES
How I contribute
I turn business goals into testable technical plans, implement the critical paths, and give the team clear module boundaries, engineering standards and ownership. From design review to production debugging, decisions are grounded in evidence and delivery has clear accountability.
Enter the real workflow and find the bottleneck that changes outcomes instead of forcing a model-first idea.
Build something usable and measurable, so the team has evidence to continue, adjust or stop.
Join frontend, backend, data, enterprise systems and models so the solution fits existing work.
Cover permissions, evaluation, logs, release and handoff so the system remains controllable after launch.
EXPERIENCE & CONFIDENTIALITY
Anonymized project experience
ANONYMIZED PROJECT EXPERIENCE
To honor confidentiality obligations and third-party rights, this section does not display the names, logos, trademarks or other identifiers of clients, collaborators or project-related organizations without the relevant rights holder's prior written permission. The following is limited to anonymized summaries of project sectors, use cases and delivery capabilities. It does not identify or imply any specific organization and does not represent any organization's endorsement, recommendation or approval of me, my services or project outcomes.
SELECTED WORK
Case studies
AI APPLICATIONS / PLATFORM ENGINEERING
Each case explains the problem it solves, how the system works, where the engineering gets hard, and my role in delivery. Choose a case directly or use the arrows to find the scenario closest to yours.
Focus the case and use Left or Right Arrow to switch; Home and End jump to the first or last case.
This selection includes independent and team projects. Roles and public facts follow wude's resume and approved information; client-sensitive material, team details and unverified outcomes are not disclosed.
PROCESS
How we work
DISCOVER. PROTOTYPE. DEPLOY. ITERATE.
Define the result to improve, the real users, available data and constraints that cannot be crossed.
Validate the critical workflow and quality so the team has evidence to continue, adjust or stop.
Complete data, permissions, failure handling, testing and release so the demo becomes an operating product.
Use feedback to refine the workflow, experience and model, then complete documentation and handoff.
PHILOSOPHY
What I believe
“Architecture must survive failures. Products must serve the business. Teams must keep delivering.”
My work spans Java microservices, AI applications and platform delivery: clarifying workflows and acceptance criteria, then engineering concurrency, queues, model integrations and deployment. As a development team lead, I also drive task decomposition, design reviews, code quality and collaboration. I stay hands-on with critical paths and make complex failures reproducible, so each delivery becomes a system the team can maintain and evolve.
PUBLIC LEARNING GUIDE
Chinese FDE learning guide
HOW TO BECOME AN FDE
This public Chinese-language guide is for developers with programming fundamentals and no prior FDE experience. Instead of memorizing a tool list, you move from role definition and skill gaps through discovery, engineering delivery, AI evaluation and production readiness, then turn the work into portfolio and interview evidence.
WHO IT IS FORLearners who can build a small service in at least one language, use Git, HTTP APIs, SQL and basic tests, and commit 8–12 hours per week to the standard path.
Distinguish FDE work from adjacent roles and write a target-role brief.
Use the six-dimension matrix and create a focused 30-day plan.
Turn an ambiguous AI request into a testable Discovery Brief.
Create the data foundation, RAG baseline, evaluation and MCP boundaries.
Cover auth, permissions, monitoring, SLOs, rollback, drills and handoff.
Convert decisions, failures and results into portfolio and interview evidence.
CAPSTONE
The guide provides a v0.1 project contract plus design and acceptance criteria. You implement the deployable, evaluable, auditable, degradable, reversible and transferable vertical slice yourself; it is not a ready-made business codebase.
Produce a Discovery Brief, versioned evaluation set, threat model, operating evidence, runbook and a reviewable portfolio evidence chain.
This is not an employment guarantee. Always check the latest requirements for your target role.CONTACT
Start a project
Available for AI delivery projects
If you have a defined use case, bring the current blocker and desired result. If you do not know where to start, describe the workflow. Send the details by email and I will use them to assess the next step.