ML Engineer (AI)

Location: Must be based in Switzerland

Company

hirify.global is a leading AI research lab building top-ranked realtime voice models that power large-scale consumer applications in health, fitness, and media.

What you will do

• Optimize realtime inference for state-of-the-art AI models.
• Develop and maintain high-performance serving frameworks and APIs.
• Scale distributed systems to handle thousands of concurrent connections.
• Take models from research to production, ensuring reliability and performance.
• Profile and tune code to maximize performance on NVIDIA GPUs.

Requirements

• Must have legal right to work in Switzerland (visa sponsorship is not available).
• Professional fluency in English (written and spoken) for daily collaboration with US teams.
• Deep understanding of inference optimization (e.g., vLLM, TRT-LLM) and model acceleration techniques.
• Proficiency in C++, CUDA, Rust, or highly optimized Python.
• Experience with distributed systems, Kubernetes, and multi-GPU/multi-node inference.

Nice to have

• PhD in CS, Physics, or Math.
• Open-source contributions to major inference engines.
• Experience with speculative decoding, paged attention, or continuous batching.

Culture & Benefits

• Flat organizational structure with fast iteration cycles.
• Focus on high-impact engineering and shipping stable, visible products.
• Support for open-source contributions and field-advancing research.
• Potential for future relocation support to the San Francisco Bay Area, subject to business needs.