Open to full-time roles and project workSAP × AI · Forward Deployed Engineer

Put AI to workinside enterprisesystems — and ship itend to end.

15 years across SAP and enterprise-system architecture, implementation and operations. Currently an SAP HR / AI technical consultant at IBM, building MCP servers, agents and full-stack tools that move AI from demo to production.

Dalian, ChinaClean Core · MCP · Agent
15yrs
SAP & enterprise systems
40%+
faster dev & test (representative)
50%
shorter integration cycle (representative)
3tools
public MCP / agent tools
Capabilities

Three delivery lines, one accountable owner.

Not three separate résumés — SAP, AI and full-stack engineering closing the loop in one project.

01

SAP implementation & integration

From HCM/HR and SuccessFactors to BTP CPI — turning business processes into operable systems.

  • SAP HR/HCM · SuccessFactors EC
  • BTP Integration Suite / iFlow
  • Clean Core · ABAP · OData
Learn more
02

AI FDE & agent tooling

Connect agents, MCP and RAG to real systems — with evals and guardrails that make them shippable.

  • MCP server · multi-role agents
  • RAG · local models · prompts
  • Evals · permissions · audit
Learn more
03

AMS operations & full-stack

Not just go-live — owning alerts, incidents, change and the iterations that follow.

  • Monitoring · incident response · release
  • Report and interface performance
  • Next.js · TypeScript · Cloudflare
Learn more
Selected work

Take complex systems apart, then ship them.

Three public MCP and agent tools covering SAP ABAP, Integration Suite and an HR workspace. Source is open to inspect and deployment steps are reproducible.

All work
AI assistant to SAP ADT through an MCP server, with design, dev and test subagentsSAP ABAP / MCPLIVEAI ASSISTANTCodex / Claudeintent + toolsMCP SERVERSAP ABAP MCP17 tools + discoverySAP ADTS/4HANArepository + compilerSUBAGENT 01DesignClean Core tiersSUBAGENT 02Developdiagnose + $TMPSUBAGENT 03Testwhere-used + ABAP UnitREAD-ONLY DEFAULTSCOPED WRITESCLEAN CORE01 / 2026
S/4HANA development inside an AI conversation

SAP ABAP MCP

A local MCP server that exposes SAP ADT search, source reading, syntax diagnostics and controlled deployment to AI coding assistants — with design, dev and test subagents guarding Clean Core boundaries.

MCPSAP S/4HANAABAP ADT
Overview
AI agent to SAP Integration Suite through 22 MCP tools, with iFlow and MPL log verificationSAP CPI / MCPLIVEAI AGENTIntent + plandesign / dev / testMCP SERVERSAP CPI MCP22 tools · 17 readSAP BTPIntegration SuiteiFlow · MPL · ODataPACKAGEInventoryread onlyIFLOWSourceedit / deployMPLLogsruntime proofSECURITYMetadatano secretsWRITEGatedallow flagDEPLOY → MPL VERIFYNO SECRET EXPORT02 / 2026
22 tools across the integration lifecycle

SAP CPI MCP

An enterprise MCP server for SAP Cloud Integration: inventory packages and iFlows, export source, deploy, read runtime logs and drill into failures — all inside an AI conversation.

MCPSAP BTPIntegration Suite
Overview
HR workstation UI to agent plugins, Prisma data and notification channelsHR WORKSTATION / AGENTSLIVEHR USER5 role viewsrecruit → HRDNEXT.JS UIWorkspacetasks + statusAGENT LAYERPlugins + LLMscreening · JD · offerDATAPrisma + SQLiteroster importJOBSState machinePENDING → DONENOTIFYHubWeCom · SMTPRESULTSJSONaudit trail4 CORE MODULESROLE-BASED VIEWS03 / 2026
An AI workspace for HR workflows

HR Workstation

A modular workspace for recruiters, HRBPs, SSC, C&B and HR directors. Plugin agents turn resume screening, JDs, interview guides, offers, automation monitoring and notifications into one traceable pipeline.

Next.jsTypeScriptPrisma
Overview
Enterprise work

Turn AI into capacity inside real systems.

Representative, anonymised projects. Client names, internal details and evidence are not published here.

2023.10 — Present

SAP × AI Agent development & operations platform

40%+faster dev & test

Wrapped SAP data dictionary, functions and transport requests into an MCP server, connected to AI coding assistants, and built a multi-role agent pipeline from analysis to code, tests and deployment checks.

MCPSAP ABAPMulti-agent
2023.11 — 2024.05

SAP BTP Integration Suite AI delivery automation

50%shorter integration cycle

Connected an AI orchestration engine to CPI through enterprise APIs, turning iFlow configuration and mapping into a loop of contract parsing, flow generation, one-click deployment and automated verification.

SAP CPIiFlowCI/CD
2023.08 — 2024.03

SuccessFactors EC integration + PIPL migration

≤4hmigration downtime · zero leakage

Designed the enterprise integration blueprint around Employee Central, connected dozens of branches through BTP CPI, and completed a compliant migration and interface rebuild for sensitive HR data.

SuccessFactorsCPIPIPL
2021.07 — Present

Korean appliance leasing group · global AMS

35%faster report execution

Owned high-concurrency ERP operations and enhancements, leading CS after-sales, engineer dispatch, membership billing reports, interfaces and enhancements.

SAP CSAMSPerformance
See full experienceRequest full CV
How I deliver

Prove value first, then scale.

Built for AI pilots, SAP integration go-lives and managed operations. Every step has an acceptance artifact.

01

Diagnose

Interview the key roles, map system/data/process constraints, and rank opportunities with a pilot recommendation.

02

Prototype

In 2–4 weeks, ship one narrow workflow on real data. Look at outcomes before building a platform.

03

Integrate & harden

Connect SAP and business systems; add permissions, audit, evals, monitoring and failure handling.

04

Handover & operate

Leave architecture, runbooks, alerts and rollback paths. The team can own it — or I can keep operating it.

Global delivery

Four languages, one accountable owner.

I own Chinese, Korean and English directly; Japanese is delivered with project partners. Cross-border experience spans Korea, Thailand and APAC clients.

ZHChineseNativeRequirements, design and delivery docs
KOKoreanBusiness / TOPIK AdvancedCan serve as primary working language
ENEnglishProfessional / CET-6Cross-border communication and technical docs
JAJapanesePartner-supportedJapanese communication with project partners

A four-language site is not a claim of four native languages. I will be explicit about language coverage, partners and ownership in our first call.

Open source

Public source. Deploy it yourself.

All three tools live on GitHub with four-language READMEs, connection diagnostics and smoke tests. Open an issue when stuck; new tools keep coming.

  • Four-language READMEs + reproducible setup
  • Issue support and a security disclosure path
  • Follow on GitHub / subscribe to releases

No LICENSE is attached yet, so these are source-available. Contact me before commercial use, redistribution or embedding.

Open source / See the toolsGitHubFollow on GitHub, subscribe to repository releases, or choose “open-source support” in the form and I will let you know when a new tool ships.
Two ways in

Hiring or building — start here.

For recruiters

AI Architect · AI Full-stack Engineer · SAP & AI Specialist

15 years in SAP and AI engineering. Target roles: AI architect, AI full-stack engineer, SAP & AI specialist. Full CV and project details on request.

Request the full CV
For teams

AI pilots & SAP delivery

From a two-week diagnosis to an eight-week pilot — validate one workflow before scaling investment.

Discuss an AI pilot
Next step

A system to ship, or a workflow to improve?

Tell me the current state, the outcome you need and your timeline. I reply within 24–48 hours and start with whether it is worth doing — and the fastest path.