MLOps Engineer (LLMOps)

Location: Fully remote or from a modern office; relocation opportunities to countries where hirify.global has offices may be available after the probation period, subject to approval.

Company

hirify.global develops large-scale products supported by ML and LLM infrastructure.

What you will do

• Design, build, and maintain an ML platform covering training, validation, deployment, monitoring, retraining, and model promotion.
• Develop AutoML infrastructure, experiment tracking, hyperparameter tuning, model evaluation, and reusable MLOps pipeline templates.
• Build feature stores and batch or real-time scoring pipelines using Airflow, MLflow, and related tooling.
• Implement ML CI/CD, infrastructure as code, containerized deployments, production monitoring, safe rollbacks, and fault-tolerant services.
• Build and operate LLM infrastructure, including vLLM, Ollama, LiteLLM, unified APIs, routing, fallback mechanisms, and controlled releases.
• Optimize GPU utilization, batching, latency, throughput, memory efficiency, cost, scalability, and reliability while integrating ML and LLM services with internal platforms and data infrastructure.

Requirements

• Hands-on experience building or operating MLOps infrastructure, ML platforms, or LLMOps infrastructure.
• Strong Python and Linux skills, including infrastructure automation and supporting service development.
• Experience with Docker, Kubernetes, container orchestration, CI/CD, and infrastructure management using Terraform, Ansible, or similar tools.
• Solid understanding of the complete ML model lifecycle, including training, validation, registration, deployment, monitoring, and retraining.
• Experience with MLflow, Airflow, Feature Stores such as Feast, or comparable technologies.
• Experience implementing monitoring, logging, alerting, troubleshooting, data drift monitoring, concept drift monitoring, and ML model performance monitoring in production.
• Understanding of batch scoring and real-time inference architectures.
• Experience integrating services with message brokers and analytical data stores.
• Experience building AutoML platforms and automating experiments with Optuna, Ray Tune, or similar tools.
• Experience deploying and operating LLMs, using vLLM, Ollama, LiteLLM, Ray, or similar tools, and managing GPU infrastructure for inference optimization.

Culture & Benefits

• Flexible work environment based on autonomy, ownership, and trust without micromanagement.
• Option to work fully remotely or from a modern office.
• Annual $2,000 benefits allowance after the probation period for health insurance upgrades, language learning, and sports activities.
• Partial reimbursement for professional training, courses, and industry conferences.
• Access to a corporate digital library and company-funded weekly online psychologist sessions.
• Relocation assistance may be available after the probation period for approved relocation to countries with company offices.