Remote AI Research Engineer: Multimodal Model Compression

Tether; Lugano; Hybrid; CHF 140,000 - 210,000; Full time

Job summary

Tether is expanding its AI research team to advance model compression and efficient deployment for multimodal AI systems, including LLMs and VLMs. You will reduce model footprint and compute cost while maintaining accuracy, using quantization, distillation, and pruning across edge devices.

The role demands deep expertise in model compression and multimodal architectures, with hands-on development, experimentation, and collaboration across teams to deliver scalable, low-memory AI solutions.

Qualifications

• Degree in Computer Science or related field; PhD in NLP/ML preferred with strong AI R&D background.
• Proven experience with PyTorch or similar frameworks.
• Hands-on expertise in model quantization, distillation and pruning.

Responsibilities

• Apply low-bit quantization to reduce model size and latency for multimodal AI models while preserving accuracy.
• Leverage knowledge distillation to transfer capabilities from larger models to smaller ones.
• Implement pruning to remove redundant parameters and attention heads.
• Analyze trade-offs between efficiency and accuracy across quantization, distillation and pruning.
• Publish findings and contribute to top-tier conferences in AI research.

Job description

Tether is expanding its AI research team to advance model compression and efficient deployment for multimodal AI systems, including LLMs and VLMs. You will reduce model footprint and compute cost while maintaining accuracy, using quantization, distillation, and pruning across edge devices.

The role demands deep expertise in model compression and multimodal architectures, with hands-on development, experimentation, and collaboration across teams to deliver scalable, low-memory AI solutions.