Edge AI Research Engineer: Multimodal Model Compression

Edge AI Research Engineer: Multimodal Model Compression

Full-Time 60000 - 80000 Β£ / year (est.) No working from home possible
T

At a Glance

  • Tasks: Innovate in AI by reducing model size and boosting efficiency for advanced systems.
  • Company: Tether, a leading AI research firm in Greater London.
  • Benefits: Competitive salary, flexible working hours, and opportunities for impactful research.
  • Other info: Be part of a dynamic environment with significant career advancement potential.
  • Why this job: Join a cutting-edge team and shape the future of AI technology.
  • Qualifications: PhD in a relevant field and experience with PyTorch required.

The predicted salary is between 60000 - 80000 Β£ per year.

Tether in Greater London is looking for an AI Researcher specializing in model compression for multimodal systems. The role involves innovation in reducing model footprint and enhancing efficiency in deploying advanced AI systems like large language models.

Responsibilities include:

  • Applying quantization and knowledge distillation techniques.

Qualifications require:

  • A PhD in a relevant field.
  • Experience with PyTorch.

This position offers the chance to contribute meaningfully in a cutting-edge area of AI research.

Edge AI Research Engineer: Multimodal Model Compression employer: Tether

Tether is an exceptional employer that fosters a culture of innovation and collaboration, making it an ideal place for an Edge AI Inference Engineer. With a strong emphasis on employee growth, Tether offers numerous opportunities for professional development and encourages team members to push the boundaries of AI technology in a supportive environment. Located in a vibrant tech hub, employees benefit from a dynamic work atmosphere and access to cutting-edge resources, ensuring that your contributions have a meaningful impact on real-world applications.

T

Contact Details:

Tether Recruitment Team

We think you need these skills to ace Edge AI Research Engineer: Multimodal Model Compression

Model Compression
Multimodal Systems
Quantization Techniques
Knowledge Distillation
PyTorch
AI System Deployment
Large Language Models