AI Research Engineer (Model Compression & Quantization)

4 months ago

Remote, WorldwideSenior

Responsibilities

Apply low-bit quantization to LLMs, VLMs, and other multimodal generative AI models while preserving accuracy and output quality.
Use knowledge distillation to transfer capabilities from large teacher models to smaller student models across text, image, and audio tasks.
Implement pruning methods to remove redundant parameters and attention heads while reducing computational overhead.
Measure and analyze trade-offs among model size, latency, memory consumption, throughput, and accuracy.
Research and implement mixed-precision quantization, adaptive pruning schedules, intermediate feature matching, and other advanced compression techniques.
Develop robust compression pipelines and address production inference bottlenecks for resource-constrained edge devices.
Stay current with research on compression for multimodal and generative architectures.
Document methodologies, experiments, and results to support reproducibility and collaboration.
Author technical papers and publish model-compression research at top-tier conferences.

Bachelor’s degree in Computer Science or a related field.
PhD in NLP, Machine Learning, or a related field is preferred.
Solid track record in AI research and development, preferably including publications at A* conferences.
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 preferred, especially for low-level quantization kernels or inference optimization.

Remote work from locations around the world.
Opportunity to work on advanced multimodal AI and model-compression research within Tether’s AI research team.
Candidates should apply through Tether’s official careers channels; recruitment communication uses official company emails and platforms.

201-500 employees