Hi, I'm Khomkrit Uprakham 👋
🌱 Currently exploring GraphRAG architectures and optimizing local LLM inference with Rust
I specialize in designing and building high-throughput backend systems, optimizing cloud-native infrastructure, and integrating Local Sovereign AI. My focus is on delivering highly scalable, memory-safe, and zero-cost abstraction solutions.
- High-Performance Engineering: Building robust systems using Clean Architecture and Domain-Driven Design (DDD).
- Cloud-Native & DevOps: Designing zero-downtime deployments, microservices orchestration, and API Gateways.
- AI & Data Infrastructure: Architecting Local LLM integrations, RAG pipelines, and highly optimized data layers without traditional ORM bottlenecks.
- Languages:
RustGoPythonTypeScript - Infrastructure:
KubernetesArgo CDAPISIXDockerTerraform - Databases:
ScyllaDBRedisQdrantPostgreSQL - AI & Machine Learning:
Local LLM InferencePyTorchGraphRAG
- Architecting a high-performance Retrieval-Augmented Generation (RAG) orchestrator in Rust for seamless AI integration.
- Designing Lightweight AI Agent framework working on specialized environment.
- Optimizing Local AI inference pipelines for sovereign data environments.
- Email: [azimuth3d@gmail.com]
- Blog: [https://khomkrit.cc]
|
|
|