Real-Time ML Infrastructure Engineer for Robotics

General Robotics; Redmond (WA); On-site; USD 155,000 - 200,000; Full time

Benefits offered by this job

Medical benefits

401K

Job summary

General Robotics in Redmond, WA is seeking an ML Engineer to join our team that builds and optimizes a real-time platform for ML models in autonomous robotics. You will focus on low latency, high throughput, and robust robot-to-cloud communication, turning research models into production services.

The role covers ML infrastructure, model serving, CUDA kernel work, and deployment across platforms using Docker, Kubernetes, Ray, and Triton.

Qualifications

• Bachelor’s degree in Computer Science, Computer Engineering, or relevant technical field, or equivalent practical experience.
• 1+ years of experience in ML infrastructure, model serving, or backend systems engineering.
• Strong Python. Comfortable navigating unfamiliar research codebases and turning them into clean, production services.

Responsibilities

• Integrate and productionize state-of-the-art ML models into our serving infrastructure, collaborating with research teams to bring new architectures from prototype to deployment.
• Develop and maintain low-latency, high-throughput pipelines for ML model inference across robotics workloads.
• Optimize GPU workloads and accelerate ML frameworks for real-time performance: data transfer, memory management, batching, serialization, and concurrent request handling.

Skills

Python

CUDA

Model serving

Realtime ML

Cloud platforms

Education

Bachelor's degree in CS or related

Tools

Docker

Kubernetes

Ray

Triton

PyTorch

JAX

Job description

General Robotics in Redmond, WA is seeking an ML Engineer to join our team that builds and optimizes a real-time platform for ML models in autonomous robotics. You will focus on low latency, high throughput, and robust robot-to-cloud communication, turning research models into production services.

The role covers ML infrastructure, model serving, CUDA kernel work, and deployment across platforms using Docker, Kubernetes, Ray, and Triton.