AI Research Engineer (Model Compression & Quantization)
Tether Operations Limited5 months ago
Remote, WorldwideSenior
Responsibilities
- Apply low-bit quantization, including Quantization-Aware Training and Post-Training Quantization, to LLMs, VLMs, and other multimodal generative AI models.
- Use knowledge distillation to transfer capabilities from larger teacher models to smaller student models across text, image, and audio tasks.
- Implement pruning methods to remove redundant parameters and attention heads while maintaining task performance.
- Measure and optimize trade-offs among model size, latency, memory consumption, throughput, and accuracy.
- Research and apply mixed-precision quantization, adaptive pruning schedules, intermediate feature matching, and other advanced compression strategies.
- Build robust model compression pipelines and address production inference bottlenecks for resource-constrained edge devices.
- Stay current with model compression research for multimodal and generative architectures.
- Document methodologies, experiments, and results to support reproducibility and internal collaboration.
- Author technical papers and publish findings at top-tier AI and machine learning conferences.
Requirements
- Bachelor’s degree in Computer Science or a related field is required; a PhD in NLP, Machine Learning, or a related field is preferred.
- Solid track record in AI research and development, ideally including publications in A* conferences.
- Hands-on experience with PyTorch or an equivalent deep learning framework.
- Hands-on experience with both Quantization-Aware Training and Post-Training Quantization.
- Research and practical experience using knowledge distillation to compress large models.
- Research and practical experience using model pruning to compress large models.
- Strong understanding of neural network architectures and training, including transformers, LLMs, VLMs, backpropagation, optimization, and fine-tuning.
- Familiarity with C++ is a plus, particularly for low-level quantization kernels or inference optimization.
Benefits
- Globally remote work with a distributed team.
- Opportunity to conduct advanced research and publish in leading conferences.
- Work focused on efficient multimodal AI deployment for edge devices and real-world applications.
Categories
AI ResearchML Engineering
About Tether Operations Limited
Tether Operations Limited develops and issues reserve-backed digital tokens used by exchanges, wallets, payment processors, and merchants, most notably the USDT stablecoin available across multiple blockchains. Founded in 2014 and privately held, it earns revenue from token issuance, reserve management, and related services, and has expanded into tokenization, peer-to-peer communications (Keet), and Bitcoin mining. USDT is widely used in crypto trading and cross-border transfers, including in emerging markets.