Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Hi, I’m Sein Him Law, an Independent AI Engineer focused on LLM systems, production-grade RAG pipelines, and tool-enabled agents. I design scalable memory architectures, multilingual embeddings, and retrieval strategies that keep essential context alive across long conversations and multilingual environments. I enjoy turning complex data problems into reliable, customer-facing systems, from end-to-end platform development (AWS, GCP, serverless, React/TypeScript) to ML pipelines and analytics, with measurable cost savings, robust monitoring, and responsible AI governance.…Hi, I’m Sein Him Law, an Independent AI Engineer focused on LLM systems, production-grade RAG pipelines, and tool-enabled agents. I design scalable memory architectures, multilingual embeddings, and retrieval strategies that keep essential context alive across long conversations and multilingual environments. I enjoy turning complex data problems into reliable, customer-facing systems, from end-to-end platform development (AWS, GCP, serverless, React/TypeScript) to ML pipelines and analytics, with measurable cost savings, robust monitoring, and responsible AI governance.

Sein Him Law





Hi, I’m Sein Him Law, an Independent AI Engineer focused on LLM systems, production-grade RAG pipelines, and tool-enabled agents. I design scalable memory architectures, multilingual embeddings, and retrieval strategies that keep essential context alive across long conversations and multilingual environments. I enjoy turning complex data problems into reliable, customer-facing systems, from end-to-end platform development (AWS, GCP, serverless, React/TypeScript) to ML pipelines and analytics, with measurable cost savings, robust monitoring, and responsible AI governance.…Hi, I’m Sein Him Law, an Independent AI Engineer focused on LLM systems, production-grade RAG pipelines, and tool-enabled agents. I design scalable memory architectures, multilingual embeddings, and retrieval strategies that keep essential context alive across long conversations and multilingual environments. I enjoy turning complex data problems into reliable, customer-facing systems, from end-to-end platform development (AWS, GCP, serverless, React/TypeScript) to ML pipelines and analytics, with measurable cost savings, robust monitoring, and responsible AI governance.

Available to hire

Hi, I’m Sein Him Law, an Independent AI Engineer focused on LLM systems, production-grade RAG pipelines, and tool-enabled agents. I design scalable memory architectures, multilingual embeddings, and retrieval strategies that keep essential context alive across long conversations and multilingual environments.

I enjoy turning complex data problems into reliable, customer-facing systems, from end-to-end platform development (AWS, GCP, serverless, React/TypeScript) to ML pipelines and analytics, with measurable cost savings, robust monitoring, and responsible AI governance.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Language

English

Advanced

Work Experience

AI Engineer at Independent

January 1, 2024 - Present

HKSoka · LLM/RAG Systems (hksoka.com/en) | Apr 2026 – Present Live production LLM platform — designed, built, deployed, and operated end-to-end. 13 models across 4 LLM providers (Claude, Grok, Kimi K3); 30M+ tokens processed; 82% of API calls fully background-automated. Built and deployed a remote MCP server (AWS Lambda) exposing HKSoka's RAG memory system via the open MCP standard — read-only retrieval, per-request audit logging; live integration with external AI clients. Multi-layer RAG memory system: user-seeded long-term context + auto-learned facts with separate retrieval quotas; nightly critical seed extraction into system prompt; bilingual embedding design for Cantonese-English retrieval; write-time quality gate + semantic deduplication at ingestion; date-aware retrieval integrates recency into ranking. Agentic model router: lightweight classifier selects model tier per message based on complexity and context; routing decisions logged per message. Token cost management: prompt caching on stable prefix — 54% cost reduction on short conversations, 80–90% on long sessions. Production billing: Stripe subscription lifecycle, token-based credit metering, referral incentive system. Stack: Claude / xAI Grok / Moonshot Kimi K3, Neon PostgreSQL, pgvector, Vercel, React/TypeScript