ML Engineer(ML Inference + Google Cloud Platform + System Design + Java Integration)

Inference & Deployment (Google Cloud Platform): Strong foundational experience evaluating inference frameworks, automating deployments, and deploying models to Google Cloud Platform (Google Cloud Platform). Performance Benchmarking & Quality: Ability to design and execute benchmarking, performance testing, and quality testing on ML models, as well as monitoring real-world behavior in production. System Design & Hybrid Architecture: Strong system design skills expected at an IC4/IC5 level. Candidates must be able to independently connect the dots across distributed systems and adapt rapidly to hybrid (on-premise + Google Cloud Platform) infrastructures. Production Integration: Experience integrating models into live production applications, particularly Java-based streaming pipelines. (Deep Java expertise is not required, but exposure is highly valued). Cross-Functional ML Knowledge: While this is not a research role, candidates need enough core ML framework knowledge (TensorFlow, PyTorch, JAX) to have meaningful technical handshakes with ML researchers and provide actionable feedback.