What you'll be doing

• Collaborate with ML Platform Engineers, Machine Learning Scientists, and domain engineers to deliver scalable ML solutions
• Deploy and operationalize ML models to production, bridging experimentation with real-world impact
• Enhance and maintain a cloud-based ML Platform on GCP using production-grade Python and Terraform
• Build and maintain CI/CD pipelines for ML model training and inference across environments
• Deploy, manage, and scale model serving endpoints on Kubernetes to ensure low-latency, high-availability inference
• Develop and host custom and open-source AI tooling to support rapid AI solution deployment
• Champion MLOps best practices including model versioning, experiment tracking, data validation, and automated retraining
• Set up observability, monitoring, and alerting for infrastructure and deployed models to ensure platform reliability
• Maintain and enhance open-source AI tools like LiteLLM and LibreChat and expand generative AI capabilities

Requirements

• 1+ year experience deploying and maintaining ML models in production
• Good understanding of MLOps principles such as experiment tracking, reproducibility, pipeline automation, model versioning, and production monitoring
• Strong hands-on Python skills with proficiency in ML/data libraries like scikit-learn, pandas, NumPy, XGBoost, LightGBM, and MLflow
• Familiarity with a major cloud platform, preferably Google Cloud Platform (GCP)
• Experience with containerization using Docker; preferably familiar with Kubernetes and Kubeflow
• Ability to switch context quickly with sharp attention to detail and adaptability to shifting priorities
• Preferably familiar with infrastructure-as-code tools such as Terraform
• Experience building and maintaining CI/CD pipelines for ML workflows