AI Accelerator Runtime Lead Principal Software Engineer

Ampere Computing LLC; Portland (OR); On-site; USD 182,000 - 273,000; Full time

Benefits offered by this job

Premium medical insurance

401K retirement plan

Unlimited flextime & 10+ paid holidays

Job summary

Ampere Computing LLC is hiring an AI Accelerator Principal Software Engineer – Runtime Library to lead the design, development, and optimization of AI runtime software that enables multiple state-of-the-art models to run efficiently on Ampere’s accelerators.

You will own end-to-end acceleration paths, collaborate with hardware and software teams, and push for high throughput, low latency inference across diverse workloads in production-like environments.

Qualifications

• Proven experience developing user-mode drivers and runtime libraries for GPUs or DL accelerators.
• Strong programming in C/C++ and systems-level concepts (memory, threading, perf profiling).
• Hands-on AI framework enablement with PyTorch, llama.cpp, or ONNX.

Responsibilities

• Lead design, development, and optimization of AI runtime software for accelerators.
• Own end-to-end acceleration paths across models and frameworks.
• Collaborate with hardware, compiler, and platform teams to match capabilities.

Skills

C/C++

Systems programming

AI accelerator experience

Linux

Education

BS CS/EE/CE or MS with 6+ years or PhD with 3+ years

Tools

PyTorch

llama.cpp

ONNX

Job description

Ampere Computing LLC is hiring an AI Accelerator Principal Software Engineer – Runtime Library to lead the design, development, and optimization of AI runtime software that enables multiple state-of-the-art models to run efficiently on Ampere’s accelerators.

You will own end-to-end acceleration paths, collaborate with hardware and software teams, and push for high throughput, low latency inference across diverse workloads in production-like environments.