Join Tether and Shape the Future of Digital Finance
At Tether, we’re not just building products, we’re pioneering a global financial revolution. Our solutions enable businesses—such as exchanges, wallets, payment processors, and ATMs—to seamlessly integrate reserve-backed tokens across blockchains. Leveraging blockchain technology, Tether allows you to store, send, and receive digital tokens instantly, securely, and globally, at a low cost. Transparency is fundamental to our operations, fostering trust in every transaction.
Innovate with Tether
Tether Finance: Our product suite includes the trusted stablecoin USDT, used by hundreds of millions worldwide, and digital asset tokenization services.
Our other initiatives include:
Tether Power: Promoting sustainable growth by optimizing excess energy for eco-friendly Bitcoin mining in geo-diverse facilities.
Tether Data: Advancing AI and peer-to-peer tech with solutions like KEET, our app for secure, private data sharing.
Tether Education: Providing access to digital learning, empowering individuals in digital and gig economies.
Tether Evolution: Merging technology and human potential to push innovation boundaries.
Why Join Us?
Our global remote team is passionate about fintech innovation. Join us to work alongside talented professionals, pushing industry standards and making a significant impact. If you excel in English communication and are eager to contribute to our innovative platform, Tether is your next destination.
Are you ready to be part of the future?
About the job:
As part of our AI model team, you will innovate in model serving and inference architectures for advanced AI systems. Your focus will be on optimizing deployment and inference for responsiveness, efficiency, and scalability across various applications, from resource-limited devices to complex multi-modal systems involving text, images, and audio.
You should have expertise in designing and optimizing model serving pipelines and inference frameworks, with a research-driven, hands-on approach to developing and testing novel strategies. Responsibilities include building inference pipelines, setting performance metrics, and resolving bottlenecks to ensure high-throughput, low-latency, scalable AI performance in real-world scenarios.
Responsibilities:
* Design and deploy high-performance model serving architectures optimized for various environments, including resource-constrained devices.
* Set and monitor performance targets such as latency, response time, and memory usage.
* Conduct inference tests in simulated and live environments, tracking key performance indicators and comparing results to benchmarks.
* Prepare test datasets and scenarios specific to low-resource deployments, ensuring comprehensive evaluation of model performance.
* Analyze and address bottlenecks in serving pipelines, focusing on efficiency and scalability for resource-limited systems.
* Collaborate with teams to integrate optimized frameworks into production, defining success metrics and ensuring continuous improvements.
Minimum qualifications:
* Degree in Computer Science or related field; PhD preferred, with a strong record in AI R&D and publications in top conferences.
* Proven experience in kernel and inference optimization on mobile devices, with measurable improvements in latency, throughput, and memory footprint.
* Deep understanding of model serving architectures and optimization techniques for low-latency, high-throughput performance.
* Expertise in CPU and GPU kernel development for mobile platforms and deploying inference pipelines on resource-constrained devices.
* Ability to apply empirical research to solve challenges in model serving, including latency and memory constraints, through robust evaluation and iterative optimization.
#J-18808-Ljbffr