LLM ROUTER
Routing layer over inference providers in sovereign regions.
Sends each request to the best vendor on cost, latency and throughput.
Live provider monitoring backs every routing decision.
Read moreClose
- Built algorithmic routing that sends each request to the best inference vendor on cost, latency and throughput.
- Added live monitoring of provider performance so routing decisions rest on real data.
- Worked across the full stack: Next.js console, Go services, PostgreSQL and Redis, secrets in HashiCorp Vault, deployed on AWS and GCP.





