About this project
it-programming / artificial-intelligence-1
Open
We're running a live production AI gateway (Go, PostgreSQL, Redis, Docker) with real traffic and Claude subscription integrations. We're seeing intermittent account-level restrictions and suspensions, and we need an experienced engineer who has actually investigated and fixed these kinds of issues before. What you'll do: Dig into real incident timelines, request logs, and platform behavior to root-cause account restrictions. Separate confirmed findings from hypotheses and upstream limitations. Build and lead a clear improvement plan (investigation priorities -> implementation -> monitoring). Improve logging, alerting, recovery procedures, and overall gateway reliability. What we're looking for: Hands-on experience investigating actual account suspensions / deactivations (not just token refresh failures). Strong preference for Claude subscription integration experience (or comparable platforms). Solid backend skills in Go + production systems (PostgreSQL, Redis, Docker). Ability to own both the investigation and the implementation. If you've dealt with account-level restrictions in production AI gateways or similar services and can walk through a concrete case (what happened, what you did, what changed), we'd like to talk. Apply by sharing a brief description of one relevant case, your role, and the outcome.
Category IT & Programming
Subcategory Artificial Intelligence
Project size Large
Delivery term: Not specified
Skills needed