Principal ML Infra Engineer - GPU Inference & C++ Systems

Franklin Fitch; Dallas (TX); On-site; USD 100,000 - 140,000; Full time

Job summary

A technology solutions provider in Dallas is seeking an AI Infrastructure Engineer with expertise in C++ and CUDA. The role involves designing and optimizing GPU-accelerated systems for deploying machine learning models in production. Ideal candidates will have a Master's or PhD, along with strong experience in GPU optimization and high-performance system design. Responsibilities include building inference pipelines, supporting model deployment, and working closely with ML researchers to ensure models are production-ready.

Qualifications

• Strong C++ expertise with experience in production-grade systems.
• Hands-on experience with CUDA programming and GPU optimization.
• Solid understanding of GPU architectures and memory management.

Responsibilities

• Design and maintain GPU-accelerated infrastructure for ML models.
• Build and optimize inference pipelines for low-latency performance.
• Support model conversion and deployment using inference runtimes.
• Partner with ML researchers to transition models to production.

Skills

C++ expertise

CUDA programming

GPU optimization

Linux

Education

Masters or PhD

Tools

TensorRT

Job description

A technology solutions provider in Dallas is seeking an AI Infrastructure Engineer with expertise in C++ and CUDA. The role involves designing and optimizing GPU-accelerated systems for deploying machine learning models in production. Ideal candidates will have a Master's or PhD, along with strong experience in GPU optimization and high-performance system design. Responsibilities include building inference pipelines, supporting model deployment, and working closely with ML researchers to ensure models are production-ready.