Senior MLOps Engineer
Core
Architect, build, and maintain production ML infrastructure and pipelines on Google Cloud Platform to enable scalable deployment and monitoring of AI models.
Role type
Senior MLOps Engineer
Builds
Scalable GCP-based ML infrastructure, high-throughput inference services, automated CI/CT pipelines, and production observability systems.
Domain
Cybersecurity / Cloud Infrastructure / Machine Learning Operations
Deliverable
production ML models
Required skills
GCP ecosystem mastery (Vertex AI, GKE, Cloud Run, IAM/VPC), Model serving (Triton, vLLM, MLflow), Workflow orchestration (Airflow, Vertex AI Pipelines), Infrastructure as Code (Terraform), Python, SQL, ML Observability (Grafana, Prometheus, drift detection)
Preferred skills
Large-scale LLM/Deep Learning inference, GCP Professional certifications, Feature stores (Feast)
Technologies
Vertex AI, GKE, GCS, Cloud Run, Triton Inference Server, vLLM, MLflow, Airflow, GitHub Actions, ArgoCD, Terraform, Docker, Kubernetes, Grafana, Prometheus
Responsibilities
Architect and manage scalable GCP-based ML infrastructure; Own end-to-end model deployment lifecycle; Build automated CI/CD/CT pipelines; Implement production observability and monitoring; Provide scalable training environments for AI engineers; Collaborate on data and feature engineering workflows; Lead transition of AI prototypes to production microservices.
Seniority
Senior, hands-on IC
