Senior Principal AI Inference Engineer - Remote/Edge

Cerence Inc.; Burlington (MA); Hybrid; USD 185,000 - 280,000; Full time

Benefits offered by this job

Annual bonus opportunity

Insurance coverage

Paid time off

Remote and/or hybrid work available

Job summary

Cerence Inc. is looking for a Sr. Principal Software Engineer to improve AI-driven technology for transportation. You will focus on enhancing ML inference pipelines, optimize performance, and lead engineering efforts in Burlington, Massachusetts.

The role requires expertise in GPU architecture, CUDA, and extensive experience in deploying ML models. Join a dynamic team committed to contributing to revolutionary automotive experiences.

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.

Responsibilities

• Optimize and deploy high-performance LLM inference pipelines.
• Own inference runtimes across data center, edge, and embedded platforms.
• Drive latency and throughput improvements that impact production products.

Skills

ML inference performance optimization

GPU architecture understanding

CUDA experience

Tools

vLLM

TensorRT-LLM

llama.cpp

QAIRT

Job description

Cerence Inc. is looking for a Sr. Principal Software Engineer to improve AI-driven technology for transportation. You will focus on enhancing ML inference pipelines, optimize performance, and lead engineering efforts in Burlington, Massachusetts.

The role requires expertise in GPU architecture, CUDA, and extensive experience in deploying ML models. Join a dynamic team committed to contributing to revolutionary automotive experiences.