Edge AI Research Scientist: Efficient Models for Real-Time Robots

Rhoda AI; Mountain View (CA); On-site; USD 100,000 - 150,000; Full time

Job summary

Rhoda AI is seeking a Research Scientist or Research Engineer in Mountain View, California, to enhance model efficiency for our intelligent robots. This role involves implementing model compression techniques and developing architectures for real-time applications. Ideal candidates are skilled in model compression and have experience with PyTorch.

Your contributions will bridge the gap between large-scale research models and real-time deployments, impacting the efficiency of every model trained and deployed.

Qualifications

• Strong understanding of model compression and architectures for large models.
• Hands-on experience with quantization and pruning applied to transformers.
• Deep knowledge of efficiency gains in modern architectures.

Responsibilities

• Research and implement model compression techniques.
• Design efficient architectures for real-time inference on hardware.
• Develop training strategies for better accuracy-efficiency tradeoffs.

Skills

Model compression

Efficient architectures

PyTorch

Quantization

Distillation

Education

PhD in ML, CS, or related field

Tools

TensorRT

CUDA

Job description

Rhoda AI is seeking a Research Scientist or Research Engineer in Mountain View, California, to enhance model efficiency for our intelligent robots. This role involves implementing model compression techniques and developing architectures for real-time applications. Ideal candidates are skilled in model compression and have experience with PyTorch.

Your contributions will bridge the gap between large-scale research models and real-time deployments, impacting the efficiency of every model trained and deployed.