Talent should have 7 years of experience with a strong foundation in ML inference, deployment, and quality validation. Should be capable of end-to-end ownership from model deployment to user impact, with the ability to quickly adapt to new technologies.
Should have strong expertise in ML benchmarking and collaboration, along with hands-on experience deploying models on cloud platforms, preferably GCP. Familiarity with Java/JVM-based systems for model integration, streaming data architectures, and hybrid (on-prem and cloud) environments is essential.
Must possess solid system design and distributed systems knowledge for troubleshooting, and hands-on experience with ML frameworks such as TensorFlow, PyTorch, or JAX