AI Research Engineer – Model Compression, Quantization

🕒 May 19

Apply Now

Find Similar Remote Jobs

Set Up Email Alert For New Jobs

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume

Tether.to

WebsiteLinkedInAll Job Openings

11 - 50 employees

Founded 2014

₿ Crypto

💳 Fintech

💸 Finance

Crypto • Fintech • Finance

Tether. to is a leading digital asset company that pioneers the use of stablecoins in the blockchain space. As the most widely adopted stablecoin, Tether tokens are designed to be pegged 1-to-1 with fiat currencies, offering a stable digital asset option for users. The platform facilitates these token transactions across multiple blockchains, enhancing cross-border transactions while maintaining transparency with daily records of total assets and reserves. Tether's initiatives include educational programs promoting digital asset usage, especially targeting regions like the Middle East, Turkey, and the Philippines. Tether thus positions itself as a disruptor in the traditional financial system by enabling a stable, efficient method of handling transactions in the digital currency world.

📋 Description

• Drive innovation in model compression and efficient deployment for advanced multimodal AI systems • Focus on reducing model footprint and computational cost while preserving accuracy • Apply and advance compression techniques such as quantization, knowledge distillation, and pruning • Build robust compression pipelines, establishing performance and fidelity metrics • Address bottlenecks in production inference • Deliver scalable, low-memory, low-latency AI systems on edge devices (i.e., smartphones) that maintain high fidelity and real-world value.

🎯 Requirements

• 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 • Familiarity with C++ is a plus (especially for implementing low-level quantization kernels or inference optimizations).

🏖️ Benefits

• Not specified