Elite Senior Principal ML Inference Engineer - Edge & CUDA

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

Benefits offered by this job

Annual bonus

Insurance coverage

Paid time off

401K

Equity awards

Remote/hybrid work

Job summary

Cerence AI is seeking a Senior Principal Software Engineer to advance the future of mobility by optimizing ML inference performance across data center, edge, and embedded platforms.

You will own inference runtimes such as vLLM, TensorRT-LLM, llama.cpp, and QAIRT, while pushing quantization and memory optimizations. This role offers remote or hybrid work options and a competitive equity package.

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

• Own inference runtimes across data center, edge, and embedded platforms.
• Optimize and deploy high-performance LLM inference pipelines.
• Extend and tune inference engines using custom CUDA kernels.
• Adapt runtimes for constrained and embedded deployment environments.

Skills

ML inference

GPU architecture

CUDA

low-level perf

Tools

vLLM

TensorRT-LLM

llama.cpp

QAIRT

Job description

Cerence AI is seeking a Senior Principal Software Engineer to advance the future of mobility by optimizing ML inference performance across data center, edge, and embedded platforms.

You will own inference runtimes such as vLLM, TensorRT-LLM, llama.cpp, and QAIRT, while pushing quantization and memory optimizations. This role offers remote or hybrid work options and a competitive equity package.