AI Research Engineer (Model Compression & Quantization)

As an AI Research Engineer focused on model compression and quantization at Tether, you will drive innovation in efficient deployment for advanced multimodal AI systems, including large language models (LLMs) and vision-language models (VLMs). Your work will reduce model footprint and computational cost while preserving accuracy, enabling high-performance AI to run efficiently across resource-constrained edge devices like smartphones.

What you'll do

• Apply low-bit quantization to reduce model size and inference latency for generative AI models (LLMs, VLMs, multimodal) while maintaining accuracy and output quality
• Leverage knowledge distillation to transfer capabilities from larger teacher models to smaller student models, enabling efficient multimodal reasoning across text, image, and audio inputs
• Implement pruning techniques to remove redundant parameters and attention heads, reducing computational overhead without sacrificing task performance
• Analyze trade-offs between model efficiency (size, latency, memory) and accuracy across quantization, distillation, and pruning methods and propose improvements based on empirical findings
• Research and apply mixed-precision quantization and other advanced compression strategies such as adaptive pruning schedules and distillation with intermediate feature matching to optimize the accuracy-performance balance
• Stay current with the latest research in model compression, including emerging techniques for multimodal and generative architectures
• Document methodologies, experiments, and results clearly to support reproducibility, internal collaboration, and stakeholder communication
• Author technical papers and publish findings in top-tier conferences such as NeurIPS, ICML, ICLR, CVPR, ACL, and AAAI to advance the field of model compression for multimodal AI

What you bring

• A degree in Computer Science or a related field, ideally a PhD in NLP, Machine Learning, or a related field, complemented by a solid track record in AI R&D with publications in A* conferences
• Experience with PyTorch deep learning frameworks or equivalent frameworks
• Hands-on experience with model quantization, including both Quantization-Aware Training (QAT) and Post-Training Quantization (PTQ)
• Research and hands-on experience with knowledge distillation for compressing large models into smaller, efficient ones
• Research and hands-on experience with model pruning for compressing large models into smaller, efficient ones
• A solid understanding of neural network architectures and training processes, including transformers (e.g., LLMs, VLMs), backpropagation, optimization, and fine-tuning techniques

Nice to have

• Familiarity with C++, especially for implementing low-level quantization kernels or inference optimizations

About Tether

Tether operates a suite of innovative fintech products, anchored by USDT, the world's most trusted stablecoin used by hundreds of millions globally. The company also operates Tether Power (Bitcoin mining and sustainable energy), Tether Data (AI and peer-to-peer infrastructure, including the KEET app), Tether Education (digital learning), and Tether Evolution (emerging technology initiatives). Tether is a global, remote-first organization serving the digital asset and blockchain ecosystem.