Zute Predictive is seeking an engineer to build and operate the routing layer that directs requests among Claude, GPT, Gemini, Grok, and customer fine-tunes. You will own latency and cost visibility, implement robust fallback and retry mechanisms, and instrument all aspects of calls with per-customer cost attribution.
You will work with forward-deployed engineers to meet per-engagement SLAs, ensuring reliable integrations even during provider incidents.
#J-18808-Ljbffr
We would love to welcome a new Latency-Driven Infrastructure Engineer for AI Services to our group in Omaha, NE, United States.
Consider building your career as a Latency-Driven Infrastructure Engineer for AI Services at Zute Predictive.
The Latency-Driven Infrastructure Engineer for AI Services position in the IT & Technology field is open for applications.
We have an opening for a Latency-Driven Infrastructure Engineer for AI Services in Omaha, NE, United States within IT & Technology.