Tether is hiring an AI Research Engineer (Model Compression & Quantization) in Dubai to drive innovation in model compression and efficient deployment for advanced multimodal AI systems, including large language models and vision-language models.
Responsibilities
- Apply low-bit quantization to reduce model size and inference latency for generative AI models while maintaining accuracy and output quality.
- Use knowledge distillation to transfer capabilities from larger teacher models to smaller student models.
- Implement pruning techniques to remove redundant parameters and attention heads and reduce computational overhead.
- Analyse trade-offs between model efficiency (size, latency, memory) and accuracy, and propose improvements based on empirical findings.
- Research and apply mixed-precision quantization and other advanced compression strategies.
- Build robust compression pipelines and establish performance and fidelity metrics.
- Document methodologies, experiments and results clearly, and author technical papers for top-tier conferences.
Requirements
- Degree in Computer Science or a related field; ideally a PhD in NLP, Machine Learning or a related field, with a solid track record in AI R&D and publications in leading conferences.
- Experience with PyTorch or equivalent deep learning frameworks.
- Hands-on experience with model quantization, including Quantization-Aware Training (QAT) and Post-Training Quantization (PTQ).
- Research and hands-on experience with knowledge distillation and model pruning.
- Solid understanding of neural network architectures and training processes, including transformers, backpropagation, optimisation and fine-tuning.
- Familiarity with C++ is a plus.
Note: Apply only through official channels. The employer never asks for any payment for employment.