AI Research Engineer – Kernel & Inference Optimization (Remote)

About the role

As a member of Tether’s AI model team, you will lead the design and optimisation of model serving and inference architectures for cutting‑edge AI systems. The role focuses on delivering highly responsive, efficient, and scalable performance across a variety of real‑world fintech applications, from lightweight models for constrained hardware to complex multi‑modal solutions.

Key responsibilities

• Design, implement and optimise model serving pipelines for production workloads.
• Develop inference frameworks that maximise throughput and minimise latency.
• Collaborate with cross‑functional teams to integrate AI models into Tether’s product ecosystem.
• Benchmark and profile kernel‑level performance, applying optimisation techniques where needed.
• Research and prototype advanced model architectures, including multi‑modal and resource‑efficient designs.

Required profile

• Strong background in AI/ML model deployment and inference engineering.
• Proven experience with performance optimisation at the kernel or low‑level software layer.
• Excellent English communication skills and ability to work fully remote with a global team.

Required skills

• Model serving pipelines
• Inference frameworks
• Advanced model architectures
• Kernel optimisation
• AI model deployment

What we offer

• 100% remote work from anywhere in the world.
• Opportunity to shape the future of digital finance with a leading stablecoin provider.
• Collaborative environment with top talent in fintech and AI.
• Competitive compensation and benefits package.