AI Model Engineer: Tether

Tether is pioneering a global financial revolution through cutting-edge solutions that empower businesses to seamlessly integrate reserve-backed tokens across blockchains. The company's innovative product suite includes the world's most trusted stablecoin, USDT, alongside initiatives in sustainable energy (Tether Power), AI and P2P technology (Tether Data), and digital learning (Tether Education). As a leader in the fintech industry, Tether boasts a lean, fast-growing global team of top talent working remotely. This is an opportunity to join an innovative platform and collaborate with the brightest minds to set new industry standards.

About the Role:
Tether is seeking an experienced AI Model Engineer with deep expertise in kernel development, model optimization, fine-tuning, and GPU acceleration. The successful candidate will be responsible for extending the inference framework to support inference and fine-tuning for Language Models, with a strong focus on mobile and integrated GPU acceleration using Vulkan.

Key responsibilities include implementing and optimizing custom inference and fine-tuning kernels, designing support for advanced quantization techniques, customizing Vulkan compute shaders, and debugging GPU acceleration issues on desktop and mobile devices. The role requires close collaboration with cross-functional teams to integrate optimized frameworks into production pipelines for edge and on-device applications.

Required Proficiencies:

Proficiency in C++ and GPU kernel programming.

Proven expertise in GPU acceleration with the Vulkan framework.

Strong background in quantization and mixed-precision model optimization.

Experience in Vulkan compute shader development.

Familiarity with LoRA fine-tuning methods and large language model architectures (e.g., Qwen, Gemma, LLaMA).

Ability to debug GPU-specific performance issues on desktop and mobile devices.