AI Research Engineer (Model Compression & Quantization)
Tether Operations Limited5 months ago
Remote, WorldwideSenior
Responsibilities
- Apply low-bit and mixed-precision quantization, including QAT and PTQ, 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 inputs.
- Implement pruning methods, including removal of redundant parameters and attention heads, to reduce computational overhead.
- Build robust model-compression pipelines and establish metrics for model efficiency, fidelity, and production inference performance.
- Analyze size, latency, memory, throughput, and accuracy trade-offs and propose improvements based on empirical results.
- Research emerging compression strategies such as adaptive pruning schedules and intermediate feature-matching distillation.
- Optimize multimodal AI systems for low-memory, low-latency deployment on edge devices.
- Document methodologies, experiments, and results to support reproducibility and internal communication.
- Author technical papers and publish model-compression research in top-tier conferences.
Requirements
- Bachelor’s degree in Computer Science or a related field.
- Ideally, a PhD in NLP, Machine Learning, or a related field, with a strong AI R&D publication record at leading conferences.
- Hands-on experience with PyTorch or equivalent deep learning frameworks.
- Hands-on experience with model quantization, including Quantization-Aware Training and Post-Training Quantization.
- Research and practical experience with knowledge distillation for model compression.
- Research and practical experience with model pruning for model compression.
- 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.
- Excellent English communication skills.
Benefits
- Remote work with a globally distributed team.
- Opportunity to work on advanced multimodal AI and model-compression research in a fintech and digital-asset company.
- Opportunity to publish findings in leading AI and machine-learning conferences.
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.