Senior ML Infrastructure Engineer (AI)

TL;DR

Senior ML Infrastructure Engineer (AI): Designing and building robust infrastructure and backend services for production-grade ML and LLM systems with an accent on scalability, reliability, and reproducibility. Focus on building and optimizing deployment pipelines, tooling for model versioning, and ensuring the production-readiness of research prototypes to improve behavioral health care quality.

Location: Tel Aviv District, Israel

Company

hirify.global develops a behavioral health CareOps automation platform that uses advanced AI to convert therapy conversations into actionable clinical insights.

What you will do

• Design and maintain production infrastructure supporting scalable ML and LLM systems.
• Develop and manage automated training and deployment pipelines for machine learning models.
• Build internal tooling for model experimentation, versioning, and reproducibility.
• Implement CI/CD workflows tailored for ML and model deployment.
• Ensure observability, reliability, and monitoring of AI systems in a production environment.
• Collaborate with data scientists to bridge the gap between research prototypes and scalable production systems.

Requirements

• 5+ years of industry experience in ML Infrastructure or Backend Engineering.
• Strong proficiency in Python development for production systems.
• Hands-on experience with cloud platforms (AWS, GCP, or Azure).
• Experience with containerization tools like Docker and Kubernetes.
• Proven track record of building CI/CD pipelines for backend or ML services.
• Experience managing LLM deployment or ML models in production environments.

Nice to have

• Experience with prompt engineering and LLM lifecycle management.
• Familiarity with data versioning tools like DVC or Pachyderm.
• Hands-on knowledge of MLOps platforms such as MLflow or Kubeflow.