Remote AI Research Engineer: Model Compression Multimodal

Tether; Ticino; Remote; CHF 120,000 - 180,000; Full time

Job summary

Tether is seeking a senior AI research engineer to advance compression for multimodal systems (text, image, audio) and efficient edge deployment. You’ll quantify model size, latency, and accuracy while expanding through quantization, distillation, and pruning techniques.

The role emphasizes experimentation, reproducible research, and contributions to leadership in AI R&D within a globally distributed team.

Qualifications

• A degree in Computer Science or related field; PhD in NLP/ML or related field preferred.
• Hands-on experience with PyTorch or equivalent frameworks.
• Experience with model quantization (QAT/PTQ), knowledge distillation, and pruning.
• Background in neural networks and training, including transformers.

Responsibilities

• Apply low-bit quantization to reduce model size and latency for multimodal AI models.
• Use knowledge distillation to transfer capabilities from larger to smaller models.
• Implement pruning techniques to remove redundant parameters and attention heads.
• Analyze trade-offs between size, latency, memory, and accuracy.
• Research mixed-precision quantization and advanced compression strategies.
• Stay current with model compression research for multimodal architectures.
• Document methodologies, experiments, and results for reproducibility.
• Publish findings in top conferences to advance multimodal AI compression.

Skills

Transformer architectures

Multimodal AI understanding

Model compression research

Experimentation & evaluation

Documentation & reproducibility

Education

Degree in Computer Science or related field

PhD in NLP/ML or related field (preferred)

Tools

PyTorch

C++

Job description

Tether is seeking a senior AI research engineer to advance compression for multimodal systems (text, image, audio) and efficient edge deployment. You’ll quantify model size, latency, and accuracy while expanding through quantization, distillation, and pruning techniques.

The role emphasizes experimentation, reproducible research, and contributions to leadership in AI R&D within a globally distributed team.