AI Research Engineer, Model Compression at Tether

Confirmed open

Research efficient multimodal model deployment for Tether, including LLM and vision-language models on edge devices. Remote locations listed for this posting: Switzerland.

Tether

Location: Remote
Employment: fulltime_permanent
Work arrangement: remote
Technologies: C++, PyTorch

Create a free application profile — Keep your skills and projects in a reusable profile. Private by default; you choose when to share. Apply for this job directly with the employer.

Role overview

Research efficient multimodal model deployment for Tether, including LLM and vision-language models on edge devices.

Responsibilities

Develop and evaluate quantization, knowledge distillation and pruning methods to reduce model size and inference cost.
Build compression pipelines and measure latency, memory, throughput and accuracy tradeoffs for production inference.

Qualifications

The role seeks machine-learning research and practical experience with PyTorch or similar frameworks.
Hands-on quantization, distillation, pruning and transformer knowledge are required; a related doctorate is preferred.

Technology in this role

PyTorch: The role seeks machine-learning research and practical experience with PyTorch or similar frameworks.

How to apply

Review the original posting and apply through the employer’s careers page.

View source and apply Apply directly

Source checked: 2026-10-22