Principal ML Engineer — Real-Time TTS & High-Performance GPUs

Inworld AI; Mountain View, Northern (CA, KY); Hybrid; USD 270,000 - 500,000; Full time

Benefits offered by this job

Relocation assistance

Job summary

Inworld AI is seeking a Staff / Principal Machine Learning Engineer, Serving, to help scale realtime TTS-2 in Mountain View, CA. You will own deployment, optimization, and reliability of high-performance inference systems across multi-GPU hardware and distributed clusters.

The role requires deep expertise in C++, CUDA, and modern serving frameworks, with a track record of shipping production ML systems. Relocation assistance is offered for the Mountain View office.

Qualifications

• Deep understanding of real-time TTS serving and multi-model inference.
• Experience with vLLM or TRT-LLM serving frameworks.
• Strong background in C++, CUDA, Rust, or optimized Python.
• Experience with Kubernetes, Ray, multi-GPU/multi-node inference.
• Public work: open-source contributions to major inference engines or write-ups.
• PhD in CS, Physics, Math, or equivalent practical experience.

Skills

Inference optimization

Model acceleration

High-performance systems

Distributed systems

Open-source contributions

Full-cycle ownership

PhD or equivalent experience

Education

PhD in CS, Physics, Math, or equivalent practical experience

Tools

Kubernetes

Ray

NVIDIA CUDA

NVIDIA GPUs

vLLM

TRT-LLM

Job description

Inworld AI is seeking a Staff / Principal Machine Learning Engineer, Serving, to help scale realtime TTS-2 in Mountain View, CA. You will own deployment, optimization, and reliability of high-performance inference systems across multi-GPU hardware and distributed clusters.

The role requires deep expertise in C++, CUDA, and modern serving frameworks, with a track record of shipping production ML systems. Relocation assistance is offered for the Mountain View office.