ML Ops Engineer

Model Deployment & Serving (ML + GenAI):

• Deploy and operate ML models and LLMs using Vertex AI, Cloud Run, and GKE.
• Automate packaging, versioning, and release of models, prompts, embeddings, and related artifacts.
• Design scalable inference architectures (sync, async, agentic), including batching and GPU/TPU autoscaling.

Pipeline Engineering & Automation:

• Build and maintain ML and GenAI workflows using Vertex AI Pipelines, Cloud Composer (Airflow), or custom orchestration.
• Implement CI/CD for ML code and GenAI artifacts (prompts, fine-tuned models, evaluation suites).
• Add automated validation for data quality, model performance, regression, and LLM evaluation metrics.

Cloud Infrastructure & Reliability:

• Build scalable training and inference environments using GCP services.
• Manage infrastructure as code using Terraform or Deployment Manager.
• Apply cost optimization, reliability, and scaling best practices.