AI Research Engineer, Model Compression & Quantization

Tether.io; España; On-site; PHP 4,914,004 - 7,371,007; Full time

Job summary

Tether.io seeks an AI Research Member to innovate in model compression and deployment for advanced multimodal AI systems, including large language models. Candidates with experience in quantization, knowledge distillation, and pruning are encouraged to apply.

A degree in Computer Science or related field is preferred. This role requires staying updated with the latest research and authoring papers to contribute to the field. Join Tether.io and enhance the efficiency of AI across edge devices.

Qualifications

• Degree in Computer Science or related field; Ph.D. in NLP, Machine Learning, or a related field preferred.
• Solid track record in AI R&D with publications in A* conferences.
• Experience with PyTorch deep learning frameworks or equivalent.
• Hands-on experience with model quantization (both QAT and PTQ).
• Hands-on experience with knowledge distillation for compressing large models into smaller, efficient ones.
• 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 (LLMs, VLMs), backpropagation, optimization, and fine-tuning.
• Familiarity with C++ is a plus, especially for implementing low-level quantization kernels or inference optimizations.

Responsibilities

• Apply low-bit quantization to reduce model size and inference latency for generative AI models while maintaining accuracy.
• Leverage knowledge distillation to transfer capabilities from larger teacher models to smaller student models.
• Implement pruning techniques to remove redundant parameters and attention heads.
• Analyze trade-offs between model efficiency and accuracy across techniques.
• Research and apply mixed-precision quantization and other advanced compression strategies.
• Stay current with the latest research in model compression for multimodal architectures.
• Document methodologies, experiments, and results clearly.
• Author technical papers to advance the field of model compression.

Job description

Tether.io seeks an AI Research Member to innovate in model compression and deployment for advanced multimodal AI systems, including large language models. Candidates with experience in quantization, knowledge distillation, and pruning are encouraged to apply.

A degree in Computer Science or related field is preferred. This role requires staying updated with the latest research and authoring papers to contribute to the field. Join Tether.io and enhance the efficiency of AI across edge devices.