AI Platform Engineer - Production AI Infra (Hybrid)

Motion Recruitment; Miami (FL); Hybrid; USD 140,000 - 210,000; Full time

Benefits offered by this job

Hybrid work environment

Ownership of production AI infra

Foundational engineering standards

Job summary

Motion Recruitment is recruiting for an AI Infrastructure Engineer in a fintech setting based in Miami, FL. The role focuses on building and operating a platform that turns AI models into reliable, secure internal services.

You will own infrastructure, GPU workloads, model serving, and CI/CD pipelines with strong emphasis on security, observability, and reliability. The position is full-time and hybrid, offering exposure to Azure, .NET-based systems, and sensitive financial data, with

Qualifications

• 5+ years in infrastructure, platform engineering, DevOps, SRE, or ML platform engineering.
• Strong experience with Microsoft Azure and AKS.
• Hands-on Docker and containerized services; production APIs and internal platforms.

Responsibilities

• Design and operate infrastructure for large-scale AI models.
• Build secure internal APIs for AI-powered apps.
• Deploy and manage GPU-based workloads across environments.
• Integrate model-serving with retrieval systems, databases, internal services and authentication.
• Maintain CI/CD pipelines for AI model and application deployments.
• Implement observability for latency, throughput, errors, and GPU usage.
• Support batch, interactive, and evaluation inference workloads.
• Collaborate with AI engineers on model fine-tuning and deployment.
• Define standards for packaging, versioning, rollout and rollback.
• Troubleshoot across applications, infrastructure, networking and storage.

Skills

5+ years experience

Azure

Kubernetes

Docker

C# / .NET

Python

APIs

CI/CD

Linux

Security/compliance

debugging complex systems

Tools

Azure Kubernetes Service (AKS)

Microsoft Azure

Docker

Job description

Motion Recruitment is recruiting for an AI Infrastructure Engineer in a fintech setting based in Miami, FL. The role focuses on building and operating a platform that turns AI models into reliable, secure internal services.

You will own infrastructure, GPU workloads, model serving, and CI/CD pipelines with strong emphasis on security, observability, and reliability. The position is full-time and hybrid, offering exposure to Azure, .NET-based systems, and sensitive financial data, with