Edge AI Model Compression & Quantization Engineer

Tether.io; United Kingdom; On-site; GBP 60,000 - 90,000; Full time

Job summary

Tether.io is seeking an AI Research Scientist to innovate in model compression and efficient deployment for advanced multimodal AI systems. The successful candidate will focus on reducing model footprint while maintaining performance across edge devices.

Your responsibilities will include employing quantization, knowledge distillation, and pruning techniques to streamline AI models, and you'll have the opportunity to publish your research in top-tier conferences.

Qualifications

• PhD in NLP, Machine Learning, or related field with publications.
• Experience with PyTorch and model quantization.
• Hands-on experience with knowledge distillation and model pruning.

Responsibilities

• Apply low-bit quantization to reduce model size and latency.
• Leverage knowledge distillation for efficient multimodal reasoning.
• Implement pruning techniques to reduce computational overhead.

Skills

Model compression techniques

Quantization

Knowledge distillation

Model pruning

Experience with PyTorch

Neural network architectures

Familiarity with C++

Education

PhD in NLP or Machine Learning

Degree in Computer Science or related field

Job description

Tether.io is seeking an AI Research Scientist to innovate in model compression and efficient deployment for advanced multimodal AI systems. The successful candidate will focus on reducing model footprint while maintaining performance across edge devices.

Your responsibilities will include employing quantization, knowledge distillation, and pruning techniques to streamline AI models, and you'll have the opportunity to publish your research in top-tier conferences.