Senior Principal AI Inference Engineer (Remote)

Cerence; United States; Hybrid; USD 185,000 - 280,000; Full time

Benefits offered by this job

Annual bonus opportunity

Insurance coverage (medical, dental,…)

Paid time off

Paid holidays

RRSP contribution

Equity awards

Remote/hybrid work options

Job summary

Cerence Inc. is seeking a Senior Principal Software Engineer in the United States to lead optimization of ML inference pipelines across data center, edge, and embedded targets.

You will drive quantisation, cache optimization, and runtime improvements to deliver low latency and high throughput for Cerence’s AI-powered mobility solutions. The role demands deep GPU hardware knowledge, hands-on CUDA development, and proven production deployment experience, with a focus on scalable,

Qualifications

• Proven experience optimizing ML inference performance in production.
• Deep understanding of GPU architecture and memory hierarchies.
• Hands-on experience with CUDA and low-level performance tuning.
• Experience deploying models beyond research environments.

Responsibilities

• Optimize and deploy high-performance ML inference pipelines.
• Own inference runtimes across data center, edge, and embedded platforms.
• Push model performance through quantisation, kernel fusion, and cache optimization.
• Drive latency and throughput improvements that directly impact production products.
• Enable efficient, reliable deployment without external vendor dependency.

Skills

ML inference optimization

GPU architecture

CUDA

Low-level performance tuning

Production deployment

Tools

vLLM

TensorRT-LLM

llama.cpp

QAIRT

Job description

Cerence Inc. is seeking a Senior Principal Software Engineer in the United States to lead optimization of ML inference pipelines across data center, edge, and embedded targets.

You will drive quantisation, cache optimization, and runtime improvements to deliver low latency and high throughput for Cerence’s AI-powered mobility solutions. The role demands deep GPU hardware knowledge, hands-on CUDA development, and proven production deployment experience, with a focus on scalable,