Summary
Luke Kerbs is a Principal AI Engineer with nine years of hands-on experience building full-stack, AI-driven products that ship—from FastAPI backends and optimized LLM inference to polished React/TypeScript chat UIs. He specializes in deploying both commercial and self-hosted LLMs (VLLM, MLX, Llama-family, Gemma, Mixtral) on NVIDIA and Apple Silicon, lowering inference costs and enabling air-gapped, regulated deployments. At PRE Security he led the productionization of an AI-native SIEM, architecting microservices, CI/CD, Kubernetes, and secure JWT/RBAC systems while translating natural-language queries into scalable log search pipelines. Comfortable owning projects end-to-end, Luke blends product-minded engineering with cloud and DevOps expertise (AWS, Terraform, GitHub Actions) and a knack for turning research ideas into reliable, cost-efficient systems. Based in Morgan Hill, CA, he thrives in fast-paced startup settings and often bridges gaps between ML research, infra optimization, and user-facing product design.
9 years of coding experience
4 years of employment as a software developer
Bachelors Mathematical Analytics and Operations Research Mathematics, Bachelors Mathematical Analytics and Operations Research Mathematics at University of California, Davis
English, Spanish