AI Research Engineer (Model Compression & Quantization)

About the role

As a member of Tether’s AI research team, you will lead the development of model compression and quantization techniques for large multimodal AI systems, including large language models (LLMs) and vision‑language models (VLMs). Your work will enable high‑performance AI to run efficiently on resource‑constrained edge devices while preserving accuracy.

Key responsibilities

• Design, implement and evaluate compression methods such as quantization, knowledge distillation and pruning for multimodal architectures.
• Optimize large language and vision‑language models for deployment on edge hardware.
• Conduct state‑of‑the‑art research, publish findings and prototype production‑ready solutions.
• Collaborate with cross‑functional teams to integrate compressed models into Tether’s AI products.

Required profile

• Deep expertise in model compression techniques.
• Strong background in multimodal model architectures, LLMs and VLMs.
• Proven research track record with publications or patents.
• Excellent English communication skills.

Required skills

• Quantization, knowledge distillation, pruning.
• Python programming.
• Deep‑learning frameworks such as TensorFlow and PyTorch.
• Experience with large language models and vision‑language models.

What we offer

• Fully remote work within a global, high‑impact fintech environment.
• Opportunity to shape cutting‑edge AI solutions for a leading stablecoin ecosystem.
• Collaboration with top researchers and engineers.