MLOps Engineer (AI)

TL;DR

MLOps Engineer (AI): Building and maintaining the infrastructure for training, deploying, and monitoring machine learning models in production with an accent on CI/CD, observability, and GPU optimization. Focus on scaling model serving infrastructure across cloud regions and ensuring enterprise-grade reliability and federal compliance.

Location: Remote (Must be based in the US)

Company

hirify.global is an AI-native engineering firm specializing in enterprise services and high-performance infrastructure for commercial and government agencies.

What you will do

• Build CI/CD pipelines for model training, evaluation, and deployment.
• Operate and scale model serving infrastructure across multiple cloud regions.
• Implement model monitoring, drift detection, and automated rollback systems.
• Manage GPU infrastructure, autoscaling, and cost optimization.
• Collaborate with security and compliance teams to meet enterprise and federal requirements.

Requirements

• Must be based in the US
• 3+ years of experience in MLOps, platform engineering, or SRE for ML systems.
• Production-level experience with Kubernetes.
• Hands-on experience with ML platforms such as Kubeflow, SageMaker, Vertex AI, or MLflow.
• Strong infrastructure-as-code skills using Terraform or Pulumi.
• Solid understanding of model serving patterns and GPU scheduling.

Nice to have

• Experience with vLLM, TensorRT-LLM, or Triton Inference Server in production.
• Experience managing multi-cluster GPU operations.
• Experience with FedRAMP, IL4/5, or other federal compliance programs.

Culture & Benefits

• Comprehensive insurance package: Medical, Dental, and Vision.
• 401(k) plan with a generous company match.
• Paid Time Off (PTO) and profit sharing.
• Access to AI productivity tools and training at no cost.
• Supportive management environment rooted in Veteran-owned company values.