Ryan Sansbury

Hello! I'm Ryan.

I'm an AI platform and full-stack engineer focused on production LLM systems: multi-provider routing, streaming UX, evals/observability, and cost governance. I built Palette—featuring auto model selection per task, budget enforcement, and cost/latency/quality logging across OpenAI/Anthropic/Google. As an analyst turned engineer with strong data modeling and performance tuning expertise, I'm known for shipping polished React/Next.js UIs and reliable Python/Flask services that drive executive decisions.

LLM Platform Engineering

Builds production AI systems with intelligent multi-provider routing, streaming interfaces, cost controls, and comprehensive observability. Implements auto model selection based on task complexity, latency requirements, and quality metrics.

Full-Stack Development

Ships polished React/Next.js applications with responsive UIs and reliable Python/Flask backend services. Delivers secure authentication, real-time streaming, and production-grade error handling with safe rollbacks.

Data Systems & Analytics

Designs dimensional SQL models, ETL pipelines with data contracts, and analytics observability dashboards. Implements performance optimization, caching strategies, and automated testing for reliable data delivery.

Business Intelligence

Leads end-to-end BI platforms with interactive dashboards, RBAC, and audit logging. Builds forecasting services with walk-forward backtests and automated retraining, reducing reporting cycles and saving hundreds of hours quarterly.

Python TypeScript JavaScript SQL React Next.js D3.js Flask Django Node.js OpenAI API Anthropic API Google AI xAI DeepSeek REST API SSE Streaming Docker Git CI/CD Azure Heroku Render PostgreSQL SQLite ETL Tailwind CSS D3.js Chart.js Bash

Contact

Location

Based in the United States

Send a Message