Machine Learning Engineer with Google Cloud Platform

About the job: Role Machine learning engineer with Google Cloud Platform

Description

• Primary platform: Google Cloud Platform for inference, deployment automation, experimentation, and sampling
• Production integration: Java-based streaming pipelines for model integration layer
• Infrastructure: Hybrid setup with on-premise streaming and Google Cloud Platform serving stacks
• Distributed systems: Working knowledge needed for debugging and end-to-end testing. Deep expertise not required
• Machine Learning frameworks: TensorFlow, PyTorch, JAX or similar frameworks

Job Responsibilities

• Solid foundation in ML inference, deployment, and quality testing
• Proven ability to quickly get up to speed on new and unfamiliar tech stacks – this is the most critical trait
• End-to-end problem-solving approach – ability to own an issue from model handoff to user-facing behavior
• Core ML knowledge to benchmark models and work with researchers
• Experience deploying models in cloud environments, preferably Google Cloud Platform
• Exposure to Java or JVM-based systems. Model integration is done in Java, deep expertise not required
• Familiarity with streaming data architectures
• Experience in hybrid cloud/on-prem environments

Requirements

• Evaluate and benchmark new ML inference frameworks to support production decisions
• Deploy models to Google Cloud Platform and integrate them into production applications and Java-based streaming pipelines
• Take ownership of deployment automation end-to-end – from model handoff to live serving
• Monitor model behavior in production for real end-users
• Design and run benchmarking, performance testing, and quality testing for ML models
• Perform model sampling to support quality evaluation and researcher feedback loops