docs: add Korean portfolio entry guides

README.md

@@ -134,10 +134,10 @@ Portfolio entry points:
 
 | Document | Korean label | Use it for |
 |---|---|---|
-| [Portfolio submission](docs/portfolio/inferedge_portfolio_submission.md) | [한국어: 포트폴리오 제출 문서](docs/portfolio/inferedge_portfolio_submission.md) | submission-ready project narrative |
-| [Resume/interview summary](docs/portfolio/inferedge_resume_interview_summary.md) | [한국어: 이력서/면접 요약](docs/portfolio/inferedge_resume_interview_summary.md) | short role-specific explanation |
-| [1-page architecture summary](docs/portfolio/inferedge_1page_architecture.md) | [한국어: 1페이지 아키텍처 요약](docs/portfolio/inferedge_1page_architecture.md) | ecosystem diagram and role split |
-| [Pipeline status](docs/portfolio/inferedge_pipeline_status.md) | [한국어: 파이프라인 상태](docs/portfolio/inferedge_pipeline_status.md) | current implementation status |
+| [Portfolio submission](docs/portfolio/inferedge_portfolio_submission.md) | [한국어: 포트폴리오 제출 문서](docs/portfolio/inferedge_portfolio_submission.ko.md) | submission-ready project narrative |
+| [Resume/interview summary](docs/portfolio/inferedge_resume_interview_summary.md) | [한국어: 이력서/면접 요약](docs/portfolio/inferedge_resume_interview_summary.ko.md) | short role-specific explanation |
+| [1-page architecture summary](docs/portfolio/inferedge_1page_architecture.md) | [한국어: 1페이지 아키텍처 요약](docs/portfolio/inferedge_1page_architecture.ko.md) | ecosystem diagram and role split |
+| [Pipeline status](docs/portfolio/inferedge_pipeline_status.md) | [한국어: 파이프라인 상태](docs/portfolio/inferedge_pipeline_status.ko.md) | current implementation status |
 
 Interview one-liner: **InferEdge is an end-to-end inference validation pipeline that converts, runs, compares, diagnoses, and decides whether an edge AI model candidate is ready to deploy.**
 

docs/portfolio/inferedge_1page_architecture.ko.md

@@ -0,0 +1,43 @@
+# InferEdge 1-Page Architecture Summary 한국어 Quick Guide
+
+언어: [English](inferedge_1page_architecture.md) | 한국어
+
+이 문서는 한국어 리뷰어가 아키텍처 경계를 빠르게 파악하기 위한 요약본이다. 대표/canonical 문서는 [InferEdge 1-Page Architecture Summary](inferedge_1page_architecture.md)이다.
+
+## 한 줄 정의
+
+InferEdge는 Edge AI 모델의 artifact provenance, real runtime execution, comparability-first evidence, report, optional diagnosis, Lab-owned deployment decision을 하나로 연결하는 local-first inference validation pipeline이다.
+
+## 구조
+
+```text
+ONNX model
+-> Forge
+-> Runtime
+-> EdgeEnv
+-> Lab
+-> optional AIGuard
+-> optional Orchestrator operation context
+```
+
+## 책임 경계
+
+| Component | 책임 | 소유하지 않는 것 |
+|---|---|---|
+| Forge | build artifact/provenance | runtime scheduling |
+| Runtime | inference execution/result export | anomaly detector, deployment decision |
+| EdgeEnv | registry/comparability/regression evidence | Lab decision, public leaderboard |
+| Lab | report/API/job/deployment decision | production SaaS infrastructure |
+| AIGuard | deterministic diagnosis evidence | final decision owner |
+| Orchestrator | queue/deadline/fallback operation context | Kubernetes/cloud orchestration |
+
+## Runtime Intelligence 흐름
+
+Runtime Intelligence는 새 repo나 monitoring SaaS가 아니다. Orchestrator operation feed, EdgeEnv telemetry/regression context, AIGuard deterministic warning evidence를 Lab report에 보존해 deployment risk를 더 쉽게 검토하게 만드는 local-first evidence extension이다.
+
+## Reviewer focus
+
+- Lab-owned deployment decision이 최종 판단 owner로 유지되는가.
+- EdgeEnv comparability-first 정책이 regression 계산 전에 보존되는가.
+- AIGuard/Orchestrator evidence가 supplemental context로 표시되는가.
+- production SaaS, cloud control plane, production remote execution으로 과장되지 않는가.

docs/portfolio/inferedge_1page_architecture.md

@@ -1,5 +1,7 @@
 # InferEdge 1-Page Architecture Summary
 
+Language: English | [한국어](inferedge_1page_architecture.ko.md)
+
 ## One-line Pitch
 
 InferEdge is an end-to-end Edge AI inference validation pipeline that builds deployment artifacts, runs edge inference, compares results, diagnoses provenance issues, and produces deployment decisions.

docs/portfolio/inferedge_pipeline_status.ko.md

@@ -0,0 +1,45 @@
+# InferEdge Pipeline Status 한국어 Quick Guide
+
+언어: [English](inferedge_pipeline_status.md) | 한국어
+
+이 문서는 한국어 리뷰어가 현재 구현 상태를 빠르게 확인하기 위한 요약본이다. 대표/canonical 문서는 [InferEdge Pipeline Status](inferedge_pipeline_status.md)이다.
+
+## 현재 완료된 것
+
+- Lab compare/report/API/job workflow와 Lab-owned deployment decision.
+- Local Studio demo evidence replay.
+- Runtime result JSON ingestion과 worker request/response contract.
+- Jetson TensorRT FP16 25W/15W fixture evidence.
+- EdgeEnv runtime telemetry/regression context ingestion.
+- AIGuard deterministic runtime warning evidence preservation.
+- Orchestrator queue/deadline/fallback context를 supplemental operation evidence로 표시.
+
+## 현재 evidence snapshot
+
+| Evidence | 값 |
+|---|---|
+| ONNX Runtime CPU FP32 demo | `45.4299 ms` mean, `49.2128 ms` p99, `22.0119 FPS` |
+| Jetson TensorRT FP16 25W demo | `10.066401 ms` mean, `15.548438 ms` p99, `99.340373 FPS` |
+| Demo speedup | 약 `4.51x` |
+| Jetson EdgeEnv preservation smoke | `device_local_starter`, `run-20260529-034704-fbf753f0`, `runtime_operation_summary` |
+
+## 아직 구현하지 않았거나 명시적으로 제외한 것
+
+- production worker daemon
+- persistent DB/queue
+- file upload
+- production frontend beyond Local Studio
+- auth/billing
+- cloud control plane
+- production remote execution
+- production observability platform
+
+## 안전한 표현
+
+현재 상태는 production SaaS 완성이 아니라, portfolio-grade local-first validation workflow와 Runtime Intelligence evidence chain이 테스트/문서/fixture로 연결된 상태다.
+
+Lab은 최종 decision owner다. EdgeEnv는 registry/comparability/regression evidence owner다. AIGuard는 deterministic evidence provider다. Orchestrator는 operation context provider다.
+
+## Jetson 필요 여부
+
+이 문서 확인과 README 링크 검증에는 Jetson 기기가 필요하지 않다. 새로운 live device-local smoke나 sustained replay evidence를 추가할 때는 Jetson 기기가 필요하다.

docs/portfolio/inferedge_pipeline_status.md

@@ -1,5 +1,7 @@
 # InferEdge Pipeline Status
 
+Language: English | [한국어](inferedge_pipeline_status.ko.md)
+
 ## Purpose
 
 This document summarizes the current portfolio status of the InferEdge multi-repository project.

docs/portfolio/inferedge_portfolio_submission.ko.md

@@ -0,0 +1,48 @@
+# InferEdge Portfolio Submission 한국어 Quick Guide
+
+언어: [English](inferedge_portfolio_submission.md) | 한국어
+
+이 문서는 한국어 리뷰어가 빠르게 맥락을 잡기 위한 요약본이다. 대표/canonical 문서는 [InferEdge Portfolio Submission](inferedge_portfolio_submission.md)이다.
+
+## 핵심 메시지
+
+InferEdgeLab은 Runtime 결과를 단순히 보여주는 도구가 아니라, runtime evidence를 비교하고 report/API/job result/deployment decision으로 정리하는 Lab-owned deployment decision layer다.
+
+InferEdge 전체 흐름은 다음처럼 읽으면 된다.
+
+```text
+Forge build provenance
+-> Runtime real execution evidence
+-> EdgeEnv registry / comparability / regression context
+-> Lab report / deployment decision
+-> optional AIGuard deterministic evidence
+-> optional Orchestrator operation context
+```
+
+## 한눈에 보는 역할 분리
+
+| Layer | Owner | Reviewer가 확인할 것 |
+|---|---|---|
+| Forge | build/provenance | artifact가 어떤 model/config에서 만들어졌는가 |
+| Runtime | execution/result export | 실제 runtime evidence가 Lab-compatible JSON으로 남았는가 |
+| EdgeEnv | registry/comparability | 비교 가능한 조건인지 먼저 판정했는가 |
+| Lab | report/deployment decision | 최종 deploy/review/blocked 판단을 Lab이 소유하는가 |
+| AIGuard | deterministic diagnosis | runtime/output warning을 근거 기반으로 설명하는가 |
+| Orchestrator | operation context | queue/deadline/fallback context가 supplemental evidence로 보존되는가 |
+
+## 강한 evidence
+
+- Local Studio demo pair: ONNX Runtime CPU FP32 `45.4299 ms` mean / `49.2128 ms` p99 / `22.0119 FPS`.
+- Jetson TensorRT FP16 25W fixture: `10.066401 ms` mean / `15.548438 ms` p99 / `99.340373 FPS`.
+- 같은 demo pair 기준 TensorRT Jetson FP16은 ONNX Runtime CPU 대비 약 `4.51x` 빠르다.
+- Jetson EdgeEnv preservation smoke는 `device_local_starter`, live `tegrastats`, `runtime_operation_summary`, EdgeEnv run evidence, AIGuard warning, Lab deployment risk report까지 이어지는 local-first artifact chain을 보여준다.
+
+## 경계
+
+이 문서는 production SaaS, production observability platform, cloud control plane, production remote execution, public leaderboard 완성을 주장하지 않는다. Runtime Intelligence는 local-first artifact/evidence chain이며, Lab-owned deployment decision을 더 설명 가능하게 만드는 확장이다.
+
+## 읽는 순서
+
+1. README의 Portfolio entry points table을 먼저 본다.
+2. 영어 canonical 문서에서 상세 evidence와 최신 수치를 확인한다.
+3. 이 한국어 quick guide로 면접/리뷰 설명의 한글 표현을 정리한다.

docs/portfolio/inferedge_portfolio_submission.md

@@ -1,5 +1,7 @@
 # InferEdge Portfolio Submission
 
+Language: English | [한국어](inferedge_portfolio_submission.ko.md)
+
 ## 1. Project Summary
 
 InferEdge는 edge AI 모델을 변환, 실행, 비교, 진단하고 최종 배포 가능 여부를 판단하는 end-to-end inference validation pipeline이다.

docs/portfolio/inferedge_resume_interview_summary.ko.md

@@ -0,0 +1,34 @@
+# InferEdge Resume and Interview Summary 한국어 Quick Guide
+
+언어: [English](inferedge_resume_interview_summary.md) | 한국어
+
+이 문서는 한국어 이력서/면접 설명을 빠르게 잡기 위한 요약본이다. 대표/canonical 문서는 [InferEdge Resume and Interview Summary](inferedge_resume_interview_summary.md)이다.
+
+## 45초 설명
+
+InferEdge는 edge AI 모델을 build provenance, real runtime execution, 비교/report, optional deterministic diagnosis, Lab-owned deployment decision까지 연결하는 inference validation pipeline입니다. 저는 Lab에서 Runtime result를 compare/report/API/job workflow/deployment decision으로 묶고, EdgeEnv의 registry/comparability/regression evidence와 AIGuard의 deterministic warning evidence를 Lab report에 보존하는 흐름을 구현했습니다. Jetson TensorRT FP16 25W fixture는 `10.066401 ms` mean, `15.548438 ms` p99, `99.340373 FPS`를 기록했고, Local Studio demo pair에서는 ONNX Runtime CPU 대비 약 `4.51x` speedup을 보여줍니다.
+
+## 역할별 강조점
+
+| 지원 역할 | 강조할 메시지 |
+|---|---|
+| AI Inference Engineer | TensorRT/ONNX Runtime evidence, latency/p99/FPS, provenance-aware compare key |
+| Embedded / Edge Engineer | Jetson evidence, power-mode context, device-local preservation smoke |
+| Backend / AI Platform | API/job/report contract, Lab-owned decision, artifact bundle traceability |
+
+## 면접에서 강하게 말할 것
+
+- 단순 benchmark가 아니라 artifact provenance -> runtime evidence -> deployment decision까지 이어지는 validation pipeline이다.
+- EdgeEnv는 비교 가능성 판단과 regression evidence를 담당하고, Lab deployment decision을 대체하지 않는다.
+- AIGuard는 LLM 추측이 아니라 deterministic evidence provider다.
+- Orchestrator operation context는 supplemental evidence이며 production scheduler 완성 주장이 아니다.
+
+## 말하지 않을 것
+
+- production SaaS 완성
+- production observability platform
+- cloud control plane
+- production remote execution
+- AIGuard가 최종 배포 판단을 자동으로 내린다는 표현
+
+정확한 표현은 "portfolio-grade local-first validation and runtime intelligence evidence pipeline"이다.

docs/portfolio/inferedge_resume_interview_summary.md

@@ -1,5 +1,7 @@
 # InferEdge Resume and Interview Summary
 
+Language: English | [한국어](inferedge_resume_interview_summary.ko.md)
+
 ## Final Resume Bullets
 
 - Built InferEdge, an end-to-end Edge AI inference validation pipeline that connects Forge build provenance, C++ Runtime execution, Lab comparison/report/API/job workflows, optional AIGuard diagnosis evidence, and Lab-owned deployment decisions.

tests/test_runtime_intelligence_bundle_manifest.py

@@ -214,32 +214,62 @@ def test_readme_internal_links_include_matching_korean_labels():
             "Portfolio submission",
             "포트폴리오 제출 문서",
             "docs/portfolio/inferedge_portfolio_submission.md",
+            "docs/portfolio/inferedge_portfolio_submission.ko.md",
         ),
         (
             "Resume/interview summary",
             "이력서/면접 요약",
             "docs/portfolio/inferedge_resume_interview_summary.md",
+            "docs/portfolio/inferedge_resume_interview_summary.ko.md",
         ),
         (
             "1-page architecture summary",
             "1페이지 아키텍처 요약",
             "docs/portfolio/inferedge_1page_architecture.md",
+            "docs/portfolio/inferedge_1page_architecture.ko.md",
         ),
         (
             "Pipeline status",
             "파이프라인 상태",
             "docs/portfolio/inferedge_pipeline_status.md",
+            "docs/portfolio/inferedge_pipeline_status.ko.md",
         ),
         (
             "docs/portfolio/edgeenv_runtime_regression_lab_handoff.md",
             "EdgeEnv 런타임 회귀 Lab handoff 문서",
             "docs/portfolio/edgeenv_runtime_regression_lab_handoff.md",
+            "docs/portfolio/edgeenv_runtime_regression_lab_handoff.md",
+        ),
+    ]
+
+    for english_label, korean_label, english_target, korean_target in link_pairs:
+        assert f"[{english_label}]({english_target})" in readme
+        assert f"[한국어: {korean_label}]({korean_target})" in readme
+
+
+def test_portfolio_entry_korean_guides_preserve_language_links_and_boundaries():
+    guide_pairs = [
+        ("inferedge_portfolio_submission.md", "inferedge_portfolio_submission.ko.md"),
+        (
+            "inferedge_resume_interview_summary.md",
+            "inferedge_resume_interview_summary.ko.md",
         ),
+        ("inferedge_1page_architecture.md", "inferedge_1page_architecture.ko.md"),
+        ("inferedge_pipeline_status.md", "inferedge_pipeline_status.ko.md"),
     ]
 
-    for english_label, korean_label, target in link_pairs:
-        assert f"[{english_label}]({target})" in readme
-        assert f"[한국어: {korean_label}]({target})" in readme
+    for english_name, korean_name in guide_pairs:
+        english_doc = REPO_ROOT / "docs" / "portfolio" / english_name
+        korean_doc = REPO_ROOT / "docs" / "portfolio" / korean_name
+        english_text = english_doc.read_text(encoding="utf-8")
+        korean_text = korean_doc.read_text(encoding="utf-8")
+
+        assert f"Language: English | [한국어]({korean_name})" in english_text
+        assert f"언어: [English]({english_name}) | 한국어" in korean_text
+        assert "대표/canonical 문서" in korean_text
+        assert "Lab-owned deployment decision" in korean_text
+        assert "production SaaS" in korean_text
+        assert "cloud control plane" in korean_text
 
 
 def test_runtime_intelligence_bundle_manifest_gate_validates_edgeenv_handoff(