Staff ML Inference Engineer — Remote (Switzerland)

HellaGoodAudio; United States; Remote; USD 172,000 - 270,000; Full time

Job summary

Inworld, a research lab and inference provider, seeks an experienced engineer to advance real-time AI inference in Switzerland. You will work on scalable serving, optimization, and distributed systems with a focus on low latency and high throughput.

This remote Switzerland role is full-time, permanent, and involves collaboration with US-based leadership. The ideal candidate has a PhD or equivalent practical experience in backend/ML systems and strong skills in C++, CUDA, Rust, Python, plus

Qualifications

• Non-trivial systems programming projects, open-source contributions to major inference engines, or deep-dive technical write-ups.
• Full-cycle ownership: you can take a model from research to production deployment.
• PhD in CS, Physics, Math, or equivalent practical experience building backend or ML systems.
• Professional fluency in English (written and spoken) is required when collaborating with US-based leadership.

Responsibilities

• Build and optimize real-time AI inference serving at scale with low latency.
• Advance model acceleration techniques like quantization, distillation, and batching.
• Contribute to distributed systems, Kubernetes-based deployments, and multi-GPU environments.
• Collaborate with research and engineering teams; contribute open-source work.

Skills

Inference optimization

Model acceleration

High performance systems

Distributed systems

Public work

Full-cycle ownership

English fluency

Education

PhD in CS/Physics/Math or equivalent

Tools

C++

CUDA

Rust

Python

Kubernetes

Ray

Job description

Inworld, a research lab and inference provider, seeks an experienced engineer to advance real-time AI inference in Switzerland. You will work on scalable serving, optimization, and distributed systems with a focus on low latency and high throughput.

This remote Switzerland role is full-time, permanent, and involves collaboration with US-based leadership. The ideal candidate has a PhD or equivalent practical experience in backend/ML systems and strong skills in C++, CUDA, Rust, Python, plus