Principal ML Engineer, Real-Time Inference on GPUs

Inworld, Inc.; Mountain View (CA); Presencial; USD 270.000 - 500.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Relocation assistance

Descripción de la vacante

Inworld, Inc. in Mountain View is seeking a Staff / Principal Machine Learning Engineer focused on Inference to design and optimize real-time AI systems.

You will own end-to-end delivery from research to production, containerize models, and push the performance of large-scale serving on NVIDIA GPUs. You should have deep expertise in C++, CUDA, Python or Rust, plus experience with Kubernetes, Ray, and model acceleration techniques.

Formación

• Inference optimization techniques for real-time serving.
• Experience with model acceleration through quantization, distillation, and caching.
• Strong background in high-performance systems on GPUs (CUDA) and optimized Python/C++/Rust.
• Familiarity with distributed systems and scalable serving (Kubernetes, Ray).
• Contributions to open-source projects or notable backend/ML system work.
• Ability to take models from research to production with end-to-end ownership.

Responsabilidades

• Take models from research to containerized production ready services.
• Optimize serving performance and ensure reliability at scale.
• Work with backend and ML infra teams to support real-time inference.
• Contribute to open-source projects or publish technical write-ups.

Conocimientos

Inference optimization

Model acceleration

High-performance systems

Distributed systems

Open-source contributions

Full-cycle ownership

Educación

PhD in CS, Physics, Math, or equivalent

Herramientas

Kubernetes

Ray

vLLM

TRT-LLM

CUDA

Python

C++

Rust

Descripción del empleo

Inworld, Inc. in Mountain View is seeking a Staff / Principal Machine Learning Engineer focused on Inference to design and optimize real-time AI systems.

You will own end-to-end delivery from research to production, containerize models, and push the performance of large-scale serving on NVIDIA GPUs. You should have deep expertise in C++, CUDA, Python or Rust, plus experience with Kubernetes, Ray, and model acceleration techniques.