Robotics AI Systems Engineer: Edge-to-Cloud Infra

General Robotics; Redmond (WA); On-site; USD 155,000 - 205,000; Full time

Job summary

General Robotics, an AI research and deployment company in Redmond, WA, is seeking a Systems Engineer to help design and optimize infrastructure for robotics workloads spanning edge devices to cloud GPU clusters. The role focuses on low-latency pipelines and scalable, production-grade systems across diverse robotics platforms.

You will work on GPU/CUDA optimization, containerized deployments with Kubernetes and Docker, and collaborate with research teams to translate model requirements into

Qualifications

• Bachelor's degree in Computer Science, Computer Engineering, Robotics, or equivalent.
• 1+ years of experience in systems engineering, software engineering, robotics, or AI/ML systems.
• Strong systems programming in C++, Rust, Go, or Python.
• Knowledge of OS, networking, and distributed systems fundamentals.
• Experience with ML frameworks (PyTorch, JAX, TensorFlow) and cloud infra (Kubernetes, Docker).
• Experience with GPU programming and CUDA optimization for ML workloads.
• Experience scaling distributed training infrastructure for large foundation models.
• Familiarity with AWS, GCP, Azure and infrastructure-as-code tooling.
• Familiarity with real-time/edge deployment for robotics.
• Experience with high-performance networking, storage, or schedulers like Slurm, Ray.
• Understanding of ML model architectures and system constraints.

Responsibilities

• Design, build, and optimize systems infrastructure spanning edge devices to cloud GPU clusters for robotics workloads.
• Develop and maintain low-latency, high-throughput pipelines for ML model training and inference.
• Architect and manage distributed systems for efficient resource utilization across heterogeneous compute environments.
• Optimize GPU/CUDA workloads and accelerate ML frameworks for robotics applications.
• Build and maintain containerized deployment pipelines using Kubernetes and Docker.
• Collaborate with research teams to translate model requirements into scalable, production‑grade systems.
• Design monitoring, profiling, and benchmarking tools to identify and resolve performance bottlenecks.
• Contribute to infrastructure tooling and open‑source efforts.

Skills

C++

Rust

Go

Python

Distributed systems

GPU programming

CUDA optimization

Kubernetes

Docker

ML frameworks

Education

Bachelor's degree in Computer Science/Engineering/Robotics or equivalent

Master's degree preferred

Tools

Kubernetes

Docker

Slurm

Ray

Job description

General Robotics, an AI research and deployment company in Redmond, WA, is seeking a Systems Engineer to help design and optimize infrastructure for robotics workloads spanning edge devices to cloud GPU clusters. The role focuses on low-latency pipelines and scalable, production-grade systems across diverse robotics platforms.

You will work on GPU/CUDA optimization, containerized deployments with Kubernetes and Docker, and collaborate with research teams to translate model requirements into