c
creatormrai

Maxim

@creatormrai

AI Systems Architect and High Performance SQLite Optimizer

Ukraine
English, Russian
About me
Systems Architect and AI Engineer specializing in low-latency, air-gapped data pipelines and custom vector search engines. I help companies eliminate high cloud costs (Pinecone, Qdrant Cloud) and meet strict GDPR/HIPAA standards with high-performance embedded infrastructure. What I deliver: - In-process vector engines with SQLite WAL mode - Sub-millisecond query paths (0.42 ms p50) - Air-gapped, privacy-first local RAG systems - Autonomous AI agent architectures with persistent memory Fast delivery, clean code, zero cloud lock-in. Let us optimize your AI!... Read more

Skills

c
creatormrai
Maxim
Offline • 

See my services

AI Integrations
I will build a custom vector database and local rag engine

Portfolio

Work experience

Lead AI Systems Architect & Embedded Engineer

RU-EN AI Content • Self-employed

Aug 2026 - Present • 3 mos

Architecting and deploying high-performance, air-gapped AI infrastructure and custom data retrieval engines for enterprise clients. Key Responsibilities & Achievements: - Designed sub-millisecond in-process vector engines (C99, SQLite WAL mode, POSIX shared memory), achieving 0.29 ms p50 latencies and 90.6% Recall@10 on OpenAI embeddings. - Implemented secure, 100% on-premise local RAG pipelines for regulated domains (FinTech, Legal, Healthcare), ensuring zero external API leakage and GDPR/HIPAA compliance. - Optimized edge AI models and autonomous agent memory layers with zero external dependencies and minimal RAM footprint (<2 MB). - Eliminated enterprise cloud lock-in and recurrent token/hosting costs by migrating workloads from proprietary vector APIs (Pinecone, Qdrant) to sovereign local nodes.