Senior ML Engineer — Real-Time Inference at Scale

Inworld; Mountain View (CA); On-site; USD 250,000 - 300,000; Full time

Benefits offered by this job

Relocation assistance

Equity

Job summary

Inworld is hiring for a full-time engineering role in Mountain View to advance real-time AI inference at scale. You will own end-to-end deployment of research models, optimize serving paths, and push hardware utilization on NVIDIA GPUs through C++, CUDA, and optimized Python code.

You will work with Kubernetes and Ray to manage multi-GPU/multi-node deployments, balancing latency, throughput, and reliability while contributing to open‑ended, high-impact projects in a collaborative, fast-moving

Qualifications

• Deep understanding of serving frameworks and optimization techniques.

Responsibilities

• Take a model from research to production-ready service.
• Containerize models and optimize serving for reliability.
• Ensure low latency and high throughput in production systems.
• Collaborate across teams to scale multi-GPU/multi-node inference.

Skills

Inference optimization

Model acceleration

High-performance systems

Distributed systems

Public work

Full-cycle ownership

PhD or equivalent

Education

PhD in CS/Physics/Math or equivalent

Tools

C++

CUDA

Rust

Python

Kubernetes

Ray

Job description

Inworld is hiring for a full-time engineering role in Mountain View to advance real-time AI inference at scale. You will own end-to-end deployment of research models, optimize serving paths, and push hardware utilization on NVIDIA GPUs through C++, CUDA, and optimized Python code.

You will work with Kubernetes and Ray to manage multi-GPU/multi-node deployments, balancing latency, throughput, and reliability while contributing to open‑ended, high-impact projects in a collaborative, fast-moving