Production ML Engineer: Scalable Inference & Deployment

Nouvells; United States; Teletrabalho; USD 120 000 - 190 000; Tempo integral

Resumo da oferta

Nouvells is looking for a Machine Learning Engineer who can turn data and ML concepts into reliable, production-ready systems. You will own the model execution lifecycle—from packaging weights to optimizing inference runtimes and building resilient APIs that serve predictions under high concurrency.

You will collaborate with data scientists, MLOps engineers, and Backend Platform developers to ensure models train reliably, deploy without regression, and serve predictions at scale in production

Qualificações

• Bachelor’s Degree and equivalent practical experience.
• Experience turning ML research into production systems.
• Familiarity with model deployment and testing practices.
• Ability to collaborate across data science and backend teams.

Responsabilidades

• Convert raw model checkpoints (PyTorch, Transformers) into optimized inference engines using ONNX Runtime, TensorRT, TorchScript, or OpenVINO.
• Profile production inference code to identify and eliminate CPU-GPU serialization bottlenecks and memory leaks.
• Build shadow-testing and canary-routing infrastructure to benchmark candidate models against live production traffic before full deployment.
• Write automated integration tests, model output regression tests, and performance load tests within CI/CD pipelines.

Conhecimentos

PyTorch

Transformers

ONNX Runtime

TensorRT

TorchScript

OpenVINO

CI/CD pipelines

Formação académica

Bachelor’s Degree and equivalent practical experience

Ferramentas

PyTorch

Transformers

ONNX Runtime

TorchScript

TensorRT

OpenVINO

Descrição da oferta de emprego

Nouvells is looking for a Machine Learning Engineer who can turn data and ML concepts into reliable, production-ready systems. You will own the model execution lifecycle—from packaging weights to optimizing inference runtimes and building resilient APIs that serve predictions under high concurrency.

You will collaborate with data scientists, MLOps engineers, and Backend Platform developers to ensure models train reliably, deploy without regression, and serve predictions at scale in production