AI Research Engineer (Model Compression & Quantization)
Job description
Member of Tether's AI research team working on model compression and efficient deployment for multimodal AI systems, including LLMs and VLMs, so high-performance AI can run on resource-constrained edge devices such as smartphones.
At a glance
- Work mode
- Remote · Netherlands
- Languages
- English
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; propose improvements based on empirical findings.
- Research and apply mixed-precision quantization and other advanced compression strategies (e.g., adaptive pruning schedules, 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 (e.g., NeurIPS, ICML, ICLR, CVPR, ACL, AAAI) to advance the field of model compression for multimodal AI.
What we're looking for
- A degree in Computer Science or related field. Ideally PhD in NLP, Machine Learning, or a related field, complemented by a solid track record in AI R&D (with good 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.
- 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++ is a plus (especially for implementing low-level quantization kernels or inference optimizations).
Your team
AI research team
Team driving innovation in model compression and efficient deployment for advanced multimodal AI systems.
Apply
About Tether Operations Limited
Join Tether and Shape the Future of Digital Finance
Tether builds cutting-edge solutions that empower businesses—from exchanges and wallets to payment processors and ATMs—to seamlessly integrate reserve-backed tokens across blockchains. Its product suite includes the stablecoin USDT, digital asset tokenization services, energy solutions for Bitcoin mining, AI and peer-to-peer technology (including the KEET app), digital education, and technology-human potential research.
Mission
Pioneering a global financial revolution by empowering businesses to seamlessly integrate reserve-backed tokens across blockchains.
Key facts
- Digital finance / blockchain
- Our team is a global talent powerhouse, working remotely from every corner of the world.
- We've grown fast, stayed lean, and secured our place as a leader in the industry.
- USDT is relied upon by hundreds of millions worldwide.
What they value
- Transparency is the bedrock of everything we do, ensuring trust in every transaction.