Edge AI Inference Engineer: Kernel & Serving

Tether; United Kingdom; Remote; GBP 80,000 - 100,000; Full time

Job summary

Tether is seeking a talented individual to join our AI model team. The role focuses on driving innovation in model serving and inference architectures for advanced AI systems. You will lead efforts to optimize model deployment and strategies for efficient performance across diverse real-world applications.

Key responsibilities include designing and deploying state-of-the-art serving architectures, managing inference tests, and analyzing and optimizing efficiency for resource-constrained environments. Strong educational background and expertise in modern AI methodologies are essential.

Qualifications

• Strong knowledge of Metal Shading Language (MSL) and experience with custom compute shaders.
• Proven experience in low‑level kernel optimizations and inference optimization on mobile devices.
• Deep understanding of modern model serving architectures.

Responsibilities

• Design and deploy state-of-the-art model serving architectures.
• Build, run, and monitor controlled inference tests.
• Analyze computational efficiency and optimize serving infrastructure.

Skills

Experience in NLP

Knowledge of Metal Shading Language (MSL)

Kernel optimizations

Inference optimization

Writing GPU kernels

Distributed inference systems

Education

PhD in NLP, Machine Learning

Degree in Computer Science

Job description

Tether is seeking a talented individual to join our AI model team. The role focuses on driving innovation in model serving and inference architectures for advanced AI systems. You will lead efforts to optimize model deployment and strategies for efficient performance across diverse real-world applications.

Key responsibilities include designing and deploying state-of-the-art serving architectures, managing inference tests, and analyzing and optimizing efficiency for resource-constrained environments. Strong educational background and expertise in modern AI methodologies are essential.