Senior AI Engineer - Linux Infra & MLOps, Hybrid NY/NJ

VY Systems; New York (NY, NJ); Hybrid; USD 165,000 - 248,000; Part time

Job summary

VY Systems is seeking an experienced AI Engineer with strong Linux administration, ML model deployment, and AI pipeline engineering expertise. You will own deployment, scaling, and maintenance of AI workloads, model serving environments, and Linux compute clusters across NY/NJ.

You will design and implement high-performance inference pipelines using Python and C++, leveraging Docker, Kubernetes, and NVIDIA tooling, while collaborating with data scientists, software engineers, and DevOps in Agile

Qualifications

• Bachelor's degree or higher in a technical field such as CS/AI/Software Engineering.
• 5–7+ years of progressive professional experience in software engineering, machine learning engineering, and Linux administration.
• Hands-on experience with Python, ML frameworks (PyTorch, TensorFlow), and AI model deployment.
• Proficiency with Linux OS installation, configuration, and shell scripting.
• Experience with Docker, Kubernetes, and GPU resource management.
• CI/CD pipelines and MLOps workflow automation.

Responsibilities

• Develop, deploy, scale, and maintain AI inference pipelines and APIs.
• Administer Linux OS and GPU compute clusters for enterprise workloads.
• Implement containerization and model serving with Docker and Kubernetes.
• Build automated MLOps pipelines and CI/CD workflows for model deployment.
• Optimize AI performance, memory, latency, and throughput in Linux environments.
• Provide advanced debugging and RCA for AI pipeline issues.
• Collaborate with data science, software, and DevOps teams in Agile sprints.
• Maintain documentation of deployment runbooks and system topologies.

Skills

Python

PyTorch

TensorFlow

Linux administration

Docker

Kubernetes

API development

CI/CD pipelines

Education

Bachelor's degree in Computer Science, AI, or related field

Tools

NVIDIA CUDA runtimes

Job description

VY Systems is seeking an experienced AI Engineer with strong Linux administration, ML model deployment, and AI pipeline engineering expertise. You will own deployment, scaling, and maintenance of AI workloads, model serving environments, and Linux compute clusters across NY/NJ.

You will design and implement high-performance inference pipelines using Python and C++, leveraging Docker, Kubernetes, and NVIDIA tooling, while collaborating with data scientists, software engineers, and DevOps in Agile