Staff / Principal Machine Learning Engineer, Serving - Switzerland

About the Position

Staff / Principal Machine Learning Engineer, Serving - Switzerland

Inworld is a research lab of top researchers and engineers, building the world’s top-ranked realtime voice models. Today, our models are the #1 ranked realtime voice models in the world, powering the largest consumer-facing AI applications across various categories. We’ve raised more than $125M from top-tier investors and have been recognized by CB Insights as one of the 100 most promising AI companies globally.

We are looking for a Staff / Principal Machine Learning Engineer to join our team in Switzerland, working remotely. This role involves optimizing realtime voice models and contributing to the development of state-of-the-art AI applications.

Responsibilities

• Optimize realtime voice models for inference.
• Implement model acceleration techniques.
• Develop high-performance systems using C++, CUDA, Rust, or optimized Python.
• Design and scale distributed systems for handling thousands of concurrent connections.
• Take full-cycle ownership of models from research to production.

Requirements

• Inference Optimization: Deep understanding of modern serving frameworks and techniques.
• Model Acceleration: Hands-on experience with quantization, distillation, caching strategies, continuous batching, paged attention, and speculative decoding.
• High-Performance Systems: Proficiency in C++, CUDA, Rust, or highly optimized Python.
• Distributed Systems & Scaling: Experience with Kubernetes, Ray, custom load balancing, multi-GPU/multi-node inference.
• Public work: Non-trivial systems programming projects, open-source contributions, or technical write-ups.
• Full-cycle ownership: Ability to containerize, optimize, and ensure reliable production of models.
• Background: PhD in CS, Physics, Math, or equivalent practical experience.
• Professional fluency in English: Required for daily collaboration with US-based teams.

Nice to Have

• Experience in optimizing realtime voice models.
• Contributions to major inference engines.
• Deep-dive technical write-ups.

We Offer

• Remote work within Switzerland.
• Full-time, permanent employment.
• Competitive compensation package.
• Opportunity for future relocation to the San Francisco Bay Area with visa and relocation support.

About the Company

Inworld is a leading AI research lab dedicated to building the world’s top-ranked realtime voice models. Our technology powers experiences for companies like NVIDIA, Microsoft Xbox, and Niantic. We value impact, performance, and reliability, and we support open-source contributions that advance the field.

Apply now to join our innovative team and contribute to the future of AI!