Senior ML Deployment Engineer - GCP Production

Valiant Technologies LLC; San Jose (CA); Presencial; USD 140.000 - 210.000; Tempo integral

Resumo da vaga

Valiant Technologies LLC in San Jose, CA invites a Machine Learning Engineer to own the end-to-end ML model lifecycle—from post-training through production. You’ll benchmark, deploy, monitor, and integrate models into live applications in a fast-moving hybrid cloud environment.

Collaborate with ML researchers and platform teams, deploy to GCP, and ensure scalable, reliable inference in Java-based pipelines.

Qualificações

• Must demonstrate end-to-end ML inference, deployment and quality testing capabilities.
• Rapidly ramp up on new and unfamiliar tech stacks.
• Own problem from model handoff to user-facing behavior.
• Core ML knowledge to benchmark models and collaborate with researchers.
• Experience deploying models in cloud environments, ideally GCP.

Responsabilidades

• Evaluate and benchmark new ML inference frameworks.
• Deploy models to GCP and integrate into production applications.
• Own deployment automation end-to-end—from model handoff to live serving.
• Monitor model performance in production for end users.
• Design and execute benchmarking and quality testing on ML models.
• Perform model sampling to support quality evaluation and researcher feedback.
• Debug issues across the full stack—from inference layer to streaming pipelines.
• Collaborate with ML researchers to provide benchmarking feedback.
• Adapt rapidly to evolving hybrid on-prem and GCP infrastructure.

Conhecimentos

ML inference

Deployment automation

Quality testing

Cloud deployment

Cross-team collaboration

Ferramentas

GCP

Java

TensorFlow

PyTorch

JAX

Descrição da vaga

Valiant Technologies LLC in San Jose, CA invites a Machine Learning Engineer to own the end-to-end ML model lifecycle—from post-training through production. You’ll benchmark, deploy, monitor, and integrate models into live applications in a fast-moving hybrid cloud environment.

Collaborate with ML researchers and platform teams, deploy to GCP, and ensure scalable, reliable inference in Java-based pipelines.