Remote AI Research Engineer: Model Compression & Multimodal

Tether Ltd.; Amsterdam; Hybrid; EUR 80,000 - 120,000; Full time

Job summary

Tether Ltd. in Amsterdam seeks an AI research specialist to advance model compression for multimodal systems, including LLMs and VLMs. You will balance size, speed, and accuracy while targeting edge devices.

You will apply quantization, distillation, and pruning, build robust pipelines, and publish findings at top conferences. Strong PyTorch experience, PhD preferred, and a track record in AI R&D are valued.

Qualifications

• A degree in Computer Science or related field. PhD in NLP/ML preferred.
• Hands-on experience with PyTorch or equivalent frameworks.
• Experience with model quantization including QAT and PTQ.

Responsibilities

• Develop and optimize compression pipelines for multimodal AI (text, image, audio).
• Apply quantization, distillation, and pruning to balance size, latency and accuracy.
• Experiment and report results with reproducible methodologies.
• Publish findings in top-tier conferences to advance model compression for multimodal AI.

Skills

PyTorch

Quantization

Distillation

Pruning

Multimodal AI

Transformers

Edge deployment

Education

Computer Science degree

PhD in NLP/ML

Tools

C++ knowledge

CUDA

Job description

Tether Ltd. in Amsterdam seeks an AI research specialist to advance model compression for multimodal systems, including LLMs and VLMs. You will balance size, speed, and accuracy while targeting edge devices.

You will apply quantization, distillation, and pruning, build robust pipelines, and publish findings at top conferences. Strong PyTorch experience, PhD preferred, and a track record in AI R&D are valued.