Edge AI Engineer - Model Compression & Quantization

Tether.io; Schweiz; Remote; CHF 120,000 - 190,000; Full time

Job summary

Tether.io is seeking an AI research Engineer to advance model compression for multimodal systems, including LLMs and VLMs. You will reduce footprint and compute costs while preserving accuracy, enabling efficient deployment on edge devices such as smartphones.

Join a remote, globally distributed team to drive benchmarking, toolchain development, and publications in top conferences. Experience with PyTorch and C++ is a plus, and a PhD or equivalent research track is preferred.

Qualifications

• PhD or equivalent research track in AI/ML with publications.
• Hands-on research and production experience in model compression.
• Experience with multimodal architectures and transformers.

Responsibilities

• Develop and optimize compression pipelines for LLMs and VLMs.
• Apply quantization, distillation, and pruning to reduce footprint.
• Balance accuracy, latency, and memory for edge devices.
• Experiment with mixed-precision and adaptive pruning schedules.
• Document methodologies and publish findings to conferences.
• Collaborate with cross‑functional teams and share results.

Skills

Model compression

Quantization

Knowledge distillation

Model pruning

Multimodal AI

Edge deployment

PyTorch

C++ (bonus)

Education

PhD in NLP/ML (preferred)

Strong publications in top conferences

Tools

PyTorch

C++

PTQ/QAT tooling

Job description

Tether.io is seeking an AI research Engineer to advance model compression for multimodal systems, including LLMs and VLMs. You will reduce footprint and compute costs while preserving accuracy, enabling efficient deployment on edge devices such as smartphones.

Join a remote, globally distributed team to drive benchmarking, toolchain development, and publications in top conferences. Experience with PyTorch and C++ is a plus, and a PhD or equivalent research track is preferred.