Kim Pyeong Gwon 김평권

Azure Data & AI Architect | Microsoft AI Solutions | AI Transformation

Email: kim@pyeonggw.one · LinkedIn: linkedin.com/in/pyeonggwon · GitHub: github.com/pyeonggwone

Azure Solution Architect with 3+ years in Data & AI. I design and land governed AI and data platforms for APAC ISVs and Microsoft partners, from Marketplace onboarding to production deployment.

I bridge sovereign-cloud and hybrid data platforms so regulated customers can run generative and agentic AI under governance. Prosci Certified Change Practitioner and Microsoft AI Transformation Leader (AB-731), aligning business and technical stakeholders for AI adoption.

Korean (Native) · English (Professional)

A hands-on architect

I do not stop at design documents. I build data platforms, review architectures, and develop products myself.

• Build → Design: I design and review Azure Data & AI architectures on the basis of data platforms I built in customer production.
• Design → Product: I turn the document-authoring and localization bottlenecks I saw repeatedly in consulting into a product (localization.md).
• Validate → Operate: I carry work past the PoC to a level that can be deployed and operated.

Key results

What I do

Customer & partner architecture

60+ APAC ISVs and 20+ strategic partners. Architecture design and review, security/cost/performance/reliability recommendations, and blocker resolution through production readiness.

Applied GenAI

Designed and built RAG over enterprise data, GPT-4o text-to-SQL agents, agentic architecture patterns, and private-network AI environments.

Hands-on engineering

Delivered lakehouse, streaming, and orchestration platforms in customer production. 150TB → 7.53TB, zero-downtime OS migration of a 7.5M-household platform.

Enablement

Microsoft Certified Trainer and Prosci CCP. Technical workshops, reference content, and change management at partner and executive level.

Explore this site

Sections

• Education — Education of Kim Pyeong Gwon: BCS (Hons) Data Science, Taylor's University dual degree with UWE Bristol (2019–2022), GPA 3.43, Dean's List.
• Experience — Experience at Avanade (Microsoft TPD) and Ourcoms: APAC ISV architecture reviews, partner consulting, and production data platforms for KT and KT Skylife.
• Consulting — 27 ISV architecture sessions and 30 one-to-one Microsoft partner engagements, summarized by problem and reasoning with customer details removed.
• Projects — Personal projects: localization.md, the document platform PoC series behind it, a reproducible single-file coding challenge, and writing on AI agents.
• localization.md — localization.md moves PDF, EPUB, PPTX, and DOCX documents into another language with their original formatting and fixes what translation breaks.
• Certifications — Microsoft, Anthropic, GitHub, and Prosci certifications, including MCT, Claude Certified Architect, AB-100, DP-700, DP-750, and Prosci CCP.

Project details

• Document platform PoC series — the predecessors of localization.md — Building a separate translator, editor, and checker for every format multiplies cost by the number of formats. I tested the hypothesis that handling every document through one common representation lets a single feature work across all formats — rebuilding it six times with a different architecture each time.
• GitHub single-file operation-line challenge — Even a metric as simple-looking as 'lines of code' cannot be measured fairly without precise rules. I designed a challenge specification anyone can reproduce and verify under the same conditions.
• PPAS backup & recovery / data lakehouse — Cut KT's PostgreSQL (PPAS) backup storage from 150TB to 7.53TB (about 95%) with Parquet on HDFS organized as Apache Iceberg tables.
• Real-time analytics platform enhancement — Moved KT Skylife's real-time analytics platform for 7.5M households from CentOS 7 to a Rocky Linux 8 HA architecture with zero downtime and a 20-node scale-out.
• MartDB generative AI data agent (GPT-4o) — A GPT-4o PoC for KT that answers natural-language questions over the PostgreSQL MartDB with RAG and text-to-SQL, cutting query turnaround from hours to seconds.
• Airflow DAG batch scheduling — Moved KT's Crontab-based Spark and stored-procedure batches to Airflow DAGs on Docker with explicit task dependencies and web-based monitoring.
• Insurance system migration from on-premises to AWS — Moved an insurer's core services from on-premises Docker hosts to AWS EC2 with security groups, least-privilege IAM, and EBS snapshot backups.
• iOS/Android QA automation — Automated high-priority cases among Hana Bank's 3,300 manual app test scenarios with Appium and Pytest, running in parallel on three Android and three iOS devices.