AI Research Engineer (Kernel & Inference Optimization)

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. Your work will ensure that AI models run efficiently, responsively and at scale across a variety of real‑world applications, from lightweight models on constrained hardware to complex multi‑modal systems handling text, images and audio.

Key responsibilities

• Design, implement and optimise model serving pipelines for high‑throughput inference.
• Develop and benchmark inference frameworks to maximise performance on diverse hardware platforms.
• Collaborate with research and engineering teams to integrate advanced model architectures into production.
• Analyse and improve latency, memory usage and scalability of AI services.
• Document best practices and contribute to internal knowledge bases.

Required profile

• Proven experience in designing and optimising model serving and inference systems.
• Strong background in advanced machine‑learning model architectures, including multi‑modal models.
• Hands‑on research mindset with the ability to prototype and evaluate new approaches.
• Excellent English communication skills and ability to work in a globally distributed remote team.

Required skills

• Model serving pipeline design.
• Inference framework optimisation.
• Advanced model architecture knowledge.

What we offer

• Fully remote work with a global talent pool.
• Opportunity to shape AI infrastructure for a leading fintech platform.
• Collaborative environment with some of the brightest minds in digital finance.