AI Research Engineer (Model Compression & Quantization) - 100% Remote Worldwide

Tether Operations Limited is seeking an AI Research Engineer to join our global team and drive innovation in model serving and inference architectures. You will focus on optimizing model deployment strategies to ensure high-performance, scalable, and efficient AI solutions across diverse environments, including resource-constrained devices.

Key responsibilities

• Design and deploy state-of-the-art model serving architectures that deliver high throughput and low latency while optimizing memory usage.
• Build, run, and monitor controlled inference tests in production environments, tracking key performance indicators like response latency and memory consumption.
• Identify and prepare high-quality test datasets and simulation scenarios tailored to real-world deployment challenges on low-resource devices.
• Analyze computational efficiency and diagnose bottlenecks in the serving pipeline to optimize infrastructure for scalability and reliability.
• Collaborate with cross-functional teams to integrate optimized inference frameworks into production pipelines for edge and on-device applications.

Requirements

• Degree in Computer Science or a related field, with a PhD in NLP or Machine Learning preferred, supported by a strong track record in AI R&D.
• Expertise in Metal Shading Language (MSL) and the ability to write custom compute shaders from scratch.
• Proven experience in low-level kernel optimizations and inference optimization on mobile devices.
• Deep understanding of modern model serving architectures, including techniques like Tensor Parallelism, Pipeline Parallelism, and Expert Parallelism.
• Strong knowledge of model optimization methods such as Pruning, Quantization, Flash attention, and Speculative Decoding.

What we offer

• The opportunity to work within a global, remote-first team of experts in the fintech and blockchain space.
• A chance to contribute to cutting-edge AI research and development that impacts millions of users worldwide.
• A collaborative environment that encourages pushing the boundaries of technology and innovation.