Section 02 — Index(5)
Projects
Scan every project's stack and measured impact at a glance — open any card for the full case study.
01Full-Stack + AI
JobMatch: Semantic Job-Matching Platform
Multi-tenant platform ranking remote jobs against your résumé via Gemini vector embeddings and pgvector.
768-dvector match0inbound portsLivemulti-tenant
Next.js 15FastAPISupabase/pgvector
Case study02AI Research
MARL-MAPS: Dynamic Multi-Agent RL for Optimized RAG
Decentralized Reinforcement Learning policy architecture eliminating RAG Context Tax.
91%less over-search42%faster inference
PythonMulti-Agent RLRAG-DDR
Case study03Full-Stack + AI
Intelligent Interview System
Low-latency candidate evaluation platform utilizing multi-agent AI consensus pipelines.
<70mscode sync46%lower API latency+12.3%answer quality
MERN StackGoogle Gemini APIWebRTC
Case study04Data Engineering
Multi-Tenant Data Pipeline System
Highly isolated, Airflow-driven ingestion system with automated LLM fault classification.
100K+records / day<5 mintenant onboarding85%+fault accuracy
Apache AirflowPostgreSQLGroq API
Case study05Data Engineering
RAG-Based Document Q&A System
Highly concurrent vector retrieval pipeline packaged for instant deployment.
Asyncconcurrent retrievalDockerinstant deploy
FastAPIPythonPinecone
Case study