Insight is looking to solve the problem of efficiently deploying, monitoring, and maintaining machine learning models in production, driving reliability and performance from development to deployment.
Requirements
- Python-based application on Google Cloud Platform (GCP)
- Vertex AI for model training, serving, and management
- Cloud Run for containerized applications
- GCP services to support the application
Responsibilities
- Model Deployment & Management: Architect and implement scalable and reliable deployment pipelines for machine learning models. You'll use Vertex AI for model training, serving, and management.
- CI/CD Automation: Build and maintain automated CI/CD pipelines to streamline the entire model lifecycle. This includes automated testing, versioning, and deployment to production.
- Infrastructure Management: Manage the underlying infrastructure for the AI agent tool, primarily using Cloud Run for containerized applications. You'll also use other relevant GCP services to support the application.
- Monitoring & Observability: Implement comprehensive monitoring, logging, and alerting systems to track model performance, resource utilization, and potential issues in real-time.
Other
- Freedom to work from another location—even an international destination—for up to 30 consecutive calendar days per year.
- Insight is an equal opportunity employer, and all qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, disability status, protected veteran status, sexual orientation or any other characteristic protected by law.
- At Insight, we celebrate diversity of skills and experience so even if you don’t feel like your skills are a perfect match - we still want to hear from you!
- Posting Notes: Remote || California (US-CA) || United States (US) || Data & AI || None || Remote ||
