Google Cloud Platform Vertex AI Sr. Data Engineer

Disqualifiers

Resumes more than 3-4 pages in length.

Generic resumes without clearly defined accomplishments or project impact.

Missing valid LinkedIn profile.

Day to Day Responsibilities

Lead the integration of machine learning models into business-critical applications using

Google Cloud Platform Vertex AI.

Collaborate with data engineers, data scientists, software engineers, and product owners to

ensure seamless model deployment and performance in production environments.

Design and implement scalable, resilient, and secure model inference pipelines using Vertex

AI, Vertex Pipelines, and related services.

Enable continuous delivery and monitoring of models via Vertex AI Model Registry, Prediction

Endpoints, and Model Monitoring features.

Optimize model serving performance, cost, and throughput under high-load, real-time, and

batch scenarios.

Automate model lifecycle management including CI/CD pipelines, retraining, versioning,

rollback, and shadow testing.

Participate in architecture reviews and advocate best practices in ML model orchestration,

resource tuning, and observability.

Required Skills

2 years - Strong experience in model integration and deployment using Google Cloud Platform Vertex AI, especially

around Vertex Pipelines, Endpoints, Model Monitoring, and Feature Store.

Expertise in scaling ML models in production, including load balancing, latency optimization,

A/B testing, and automated retraining pipelines.

Proficiency in MLOps and model operationalization techniques, with knowledge of

infrastructure-as-code and containerized environments.

Software Skills

Required:

Google Cloud Platform Vertex AI Suite (including Pipelines, Feature Store, Model Monitoring)

Python (with emphasis on integration frameworks and automation)

Git, Docker, Poetry, Terraform or Deployment Manager

BigQuery, Dataflow, and Cloud Functions

Monitoring tools (Stackdriver, Prometheus, etc.)

Preferred Skills

Experience with MLOps tools such as Kubeflow, MLFlow, or TFX.

Familiarity with enterprise monitoring tools like Prometheus, Grafana, or Stackdriver for ML observability.

Exposure to hybrid or federated model deployment architectures.