Staff ML Engineer: Real-Time Multimodal Inference (Remote)

Inworld AI; Schweiz; On-site; CHF 100,000 - 140,000; Full time

Job summary

A leading AI research lab is seeking a highly skilled individual for a remote position in Switzerland focused on inference optimization and high-performance systems. The ideal candidate will have a PhD in a relevant field and experience with advanced techniques in machine learning. Responsibilities include clarifying complex problems and optimizing solutions for production. Proficiency in English is essential for collaboration across teams. This role does not offer visa sponsorship but may provide relocation support in the future.

Qualifications

• Deep understanding of modern serving frameworks and techniques like vLLM or TRT-LLM.
• Hands-on experience with quantization, distillation, and caching strategies.
• Proficiency in C++, CUDA, Rust, or optimized Python.

Responsibilities

• Make unclear problems clear and design benchmarks or prototypes.
• Optimize models for production and ensure reliability.
• Collaborate closely with US-based leadership and engineering teams.

Skills

Inference Optimization

Model Acceleration

High-Performance Systems

Distributed Systems & Scaling

Public work

Full-cycle ownership

Strong problem-solving skills

Professional fluency in English

Education

PhD in CS, Physics, Math, or equivalent

Job description

A leading AI research lab is seeking a highly skilled individual for a remote position in Switzerland focused on inference optimization and high-performance systems. The ideal candidate will have a PhD in a relevant field and experience with advanced techniques in machine learning. Responsibilities include clarifying complex problems and optimizing solutions for production. Proficiency in English is essential for collaboration across teams. This role does not offer visa sponsorship but may provide relocation support in the future.