Future of Digital Finance
We're pioneering a global financial revolution, empowering businesses to seamlessly integrate reserve-backed tokens across blockchains.
Innovate with Us
Our product suite includes the trusted stablecoin USDT, used by hundreds of millions, and digital asset tokenization services.
Towards Sustainable Growth:
We optimize excess power for eco-friendly Bitcoin mining in geo-diverse facilities.
Advancing AI and peer-to-peer tech, we reduce infrastructure costs with solutions like KEET, our secure data sharing app.
Why Join Us?
Our global team works remotely worldwide. If you're passionate about fintech innovation, this is your chance to collaborate with top talent, push boundaries, and set industry standards.
About the Job:
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.
We expect expertise in designing and optimizing model serving pipelines, inference frameworks, and advanced architectures.
Your Responsibilities:
* Design high-performance model serving architectures optimized for diverse environments.
* Establish performance targets such as reduced latency and memory footprint.
* Build and monitor inference tests in simulated and live environments.
* Create high-quality test datasets and scenarios to evaluate model performance under operational conditions.
* Analyze and diagnose bottlenecks in serving pipelines, addressing issues like batch processing and network delays.
* Collaborate with teams to integrate optimized frameworks into production pipelines.
A degree in Computer Science or related field is required, with a PhD preferred. Proven experience in kernel and inference optimization is essential, with a record of improving latency, throughput, and memory usage.