Senior Staff Software Engineer - AI/ML Inference Engineering

Lead the architecture, optimization, and operational excellence of ServiceNow's AI inference platform. Own end-to-end inference lifecycle from model onboarding to production deployment across multiple backends on Kubernetes. Architect intelligent gateway layer using Envoy for access control, observability, and request routing.

Expertise in Go or Python, OOP, design patterns, and efficient algorithms. Experience with model-serving systems like vLLM, TensorRT-LLM, Triton Inference Server. 8+ years backend software engineering, 4+ years distributed systems. Bachelor's in CS or related field. Desired: Kubernetes, Helm, CI/CD, observability, production incident debugging.