Senior Staff AI/ML Inference Engineer (Kubernetes & GPU)

ServiceNow; Kirkland (WA); Vor Ort; USD 201.000 - 352.000; Vollzeit

Benefits dieser Stelle

Health plans

401(k) Match

ESPP

Matching donations

Flexible time away plan

Family leave programs

Zusammenfassung

ServiceNow in Kirkland, WA is seeking a Senior Staff Software Engineer - AI/ML Inference Engineering to lead architecture, optimization, and operational excellence of our AI inference platform.

You will own the end-to-end inference lifecycle—from onboarding cutting-edge models to deploying optimized inference engines across Kubernetes backends, and you will architect the intelligent gateway layer using Envoy to enforce access control, observability, and advanced routing.

Qualifikationen

• Advanced backend software engineering experience with Go or Python.
• Experience with model-serving runtimes and ML inference tech.
• Exposure to LLM APIs or ML-serving systems.
• Experience building products with complex algorithms.
• Strong object-oriented and modular software design skills.
• Solid foundation in AI/ML techniques and algorithms.
• Experience in testing, profiling, and tuning code.

Aufgaben

• Lead architecture, optimization, and ops of the AI inference platform.
• Own end-to-end inference lifecycle from onboarding models to deployment.
• Architect gateway layer using Envoy for access control and observability.
• Work with GPU compute, LLM APIs, inference frameworks, containers, and orchestration.
• Drive measurable performance impact and reliability.

Kenntnisse

Go or Python

OOP

Design Patterns

Algorithms

Model-serving & runtime

LLM APIs / ML-serving

Product-focused development

Software quality

AI/ML techniques

Unit testing / profiling

Ausbildung

Bachelor’s degree in CS/SE or related field

Master’s degree (optional offset)

Tools

vLLM

TensorRT-LLM

Triton Inference Server

Envoy

Jobbeschreibung

ServiceNow in Kirkland, WA is seeking a Senior Staff Software Engineer - AI/ML Inference Engineering to lead architecture, optimization, and operational excellence of our AI inference platform.

You will own the end-to-end inference lifecycle—from onboarding cutting-edge models to deploying optimized inference engines across Kubernetes backends, and you will architect the intelligent gateway layer using Envoy to enforce access control, observability, and advanced routing.