Brent Oakes

I am a Senior AI Full-Stack Engineer with 7+ years of experience shipping AI-powered products in fast-moving startup environments, focusing on LLM agents, real-time voice AI agents, and generative AI embedded in customer-facing SaaS platforms. I design and implement end-to-end solutions across the stack — from React front ends to low-latency AI back ends — translating ideas into production-ready, scalable features.

My notable achievements include building LLM-powered clinical decision-support products, engineering HIPAA-compliant LLM inference and ML workflows on AWS Bedrock/SageMaker, and delivering high-performance APIs that handle 1,000+ concurrent AI inference requests with sub-300ms latency. I optimize GenAI infrastructure through caching, batching, and streaming inference to reduce costs and improve accuracy.