Staff / Principal Machine Learning Engineer, Serving
Inworld AI is a research lab and inference provider for realtime AI at consumer scale. It provides text-to-speech, speech-to-text, speech-to-speech, and LLM routing products for developers and businesses building consumer-facing applications.
Maintainer signals as of 9/25/2026
Funding history
Projects
About Inworld AI
Inworld AI develops and operates realtime AI infrastructure, including first-party text-to-speech and speech-to-text models, a customizable speech-to-speech Realtime API, and an LLM Router that routes requests across leading model providers. Its platform supports voice agents, social and companion applications, learning and education, health and wellness, agentic workforce applications, and games and media. The company serves developers, businesses, and teams building consumer-facing applications.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
Own the full lifecycle of research models by containerizing, optimizing, and operating their serving infrastructure in production. Build sub-second multimodal inference systems using model acceleration techniques and distributed infrastructure capable of handling thousands of concurrent connections.
Requirements
- Deep understanding of modern serving frameworks like vLLM or TRT-LLM
- Hands-on experience with quantization, distillation, caching strategies, continuous batching, paged attention, and speculative decoding
- Proficiency in C++, CUDA, Rust, or highly optimized Python
- Experience with Kubernetes, Ray, custom load balancing, and multi-GPU/multi-node inference
- Public work such as open-source contributions or technical write-ups
- Full-cycle ownership experience taking models to production
- PhD in CS, Physics, Math, or equivalent practical experience
- Professional fluency in English
- Legal right to work in Switzerland
Responsibilities
- Take models from the research team to production
- Containerize and optimize model serving
- Optimize inference using quantization, distillation, caching, continuous batching, paged attention, and speculative decoding
- Build distributed serving infrastructure across multiple GPUs and nodes
- Handle thousands of concurrent connections reliably
- Profile code and optimize performance on NVIDIA GPUs
- Design benchmarks and prototypes to resolve open questions
- Contribute to open-source projects and technical write-ups
Benefits
- Remote work
- Full U.S. visa and relocation support may be available for those interested in relocating to the San Francisco Bay Area