Remote AI Research Engineer — Multimodal Model Compression

Tether.io; España; Remote; EUR 70,000 - 120,000; Full time

Job summary

Tether seeks an AI research engineer to advance model compression for multimodal AI systems, including large language models and vision-language models. You will design and implement quantization, distillation, and pruning to reduce size and latency on edge devices while preserving accuracy.

You will build compression pipelines, evaluate performance, publish findings, and collaborate with global teams in a remote fintech environment that values rapid innovation.

Qualifications

• Degree in Computer Science or related field; PhD preferred with AI R&D publications.
• Hands-on experience with PyTorch or equivalent frameworks.
• Experience with model quantization (QAT/PTQ), distillation and pruning.
• Strong knowledge of transformers and multimodal architectures.
• Good publications in AI conferences; familiarity with C++ is a plus.

Responsibilities

• Apply low-bit quantization to reduce model size and inference latency while maintaining accuracy.
• Leverage knowledge distillation to transfer capabilities across large to small models.
• Implement pruning to remove redundant parameters and attention heads.
• Analyze trade-offs between efficiency and accuracy across methods; propose improvements.
• Research mixed-precision quantization and advanced compression strategies.
• Stay current with multimodal and generative AI research and publish findings.
• Document methodologies and results to support reproducibility and collaboration.
• Publish technical papers at top conferences to advance model compression.

Skills

PyTorch

Quantization

Knowledge Distillation

Model Pruning

Transformers

Multimodal AI

Edge Deployment

Research Publications

Education

Bachelor's degree in Computer Science or related field

PhD in NLP, Machine Learning or related field (preferred)

Tools

PyTorch

C++

Job description

Tether seeks an AI research engineer to advance model compression for multimodal AI systems, including large language models and vision-language models. You will design and implement quantization, distillation, and pruning to reduce size and latency on edge devices while preserving accuracy.

You will build compression pipelines, evaluate performance, publish findings, and collaborate with global teams in a remote fintech environment that values rapid innovation.