Senior Principal AI Inference Software Architect

Ampere; Durham (NC); Vor Ort; USD 226.000 - 339.000; Vollzeit

Benefits dieser Stelle

Health insurance

401K retirement plan

Unlimited Flextime

Zusammenfassung

Ampere in Durham, NC is seeking a Sr. Principal Machine Learning Software Engineer to lead the architecture and development of high-performance AI inference-serving software for Ampere accelerators.

You will drive end-to-end serving performance, collaborate across model-serving, frameworks, compilers, runtimes, and hardware teams, and mentor engineers while shaping the AI software stack for scalable, production-ready solutions.

Qualifikationen

• Experience with production inference runtimes and serving engines.
• Strong low-level systems debugging and profiling.
• Experience with multi-device or distributed inference.

Aufgaben

• Lead architecture and development of high-performance AI inference-serving software.
• Collaborate across model-serving, frameworks, compilers, runtimes, and hardware teams.
• Mentor engineers and drive technical decisions.

Kenntnisse

C++ optimization

Inference systems

Cross-functional leadership

Ausbildung

Bachelor’s degree in CS/EE

Master’s degree in CS/EE

PhD in related field

Tools

CUDA

TensorRT/TensorRT-LLM

ONNX Runtime

Jobbeschreibung

Ampere in Durham, NC is seeking a Sr. Principal Machine Learning Software Engineer to lead the architecture and development of high-performance AI inference-serving software for Ampere accelerators.

You will drive end-to-end serving performance, collaborate across model-serving, frameworks, compilers, runtimes, and hardware teams, and mentor engineers while shaping the AI software stack for scalable, production-ready solutions.