Senior AI Research Engineer, Model Inference

About the Job:
Join Tether and help shape the future of digital finance. As a Senior AI Research Engineer, you will play a crucial role in advancing our AI capabilities. Your primary responsibility will be to extend the inference framework for language models with a strong emphasis on mobile and integrated GPU acceleration (Vulkan). This position requires hands-on experience with quantization techniques, LoRA architectures, and mobile GPU debugging, positioning you at the forefront of next-generation small and large language model (SLM/LLM) inference and fine-tuning performance.

Responsibilities:

• Implement and optimize custom inference and fine-tuning kernels for language models across various hardware backends.
• Design and extend datatype and precision support for various numerical formats.
• Customize and optimize Vulkan compute shaders for quantized operators and fine-tuning workflows.
• Investigate and resolve GPU acceleration issues on Vulkan and integrated/mobile GPUs.
• Architect support for advanced quantization techniques to enhance efficiency and memory usage.
• Conduct GPU testing across desktop and mobile devices and collaborate with research and engineering teams.

Requirements:

• Proficiency in C++ and GPU kernel programming.
• Expertise in GPU acceleration using Vulkan framework.
• Strong background in quantization and mixed-precision model optimization.
• Familiarity with large language model architectures (e.g., Qwen, Gemma, LLaMA).
• Experience with mobile GPU acceleration and model inference.
• Excellent English communication skills.

Work Conditions:

• Full-time remote position.

Join us in pioneering solutions that empower businesses globally through innovative technology and a commitment to transparency. If you're ready to contribute to a leading fintech platform, apply today!