Senior ML Platform Engineer: Production & Ops

99x; Oslo fylke; Presencial; NOK 1 600 000 - 2 000 000; Tempo integral

Resumo da oferta

99x is seeking a Senior Machine Learning Engineer to build, deploy, and operate ML systems in production. You will own ML pipelines, data preparation, model deployment, and monitoring across the lifecycle, partnering with data scientists and software teams to improve reliability at scale.

The role emphasizes production engineering and cloud platforms, with a focus on scalable, observable ML services and cost-efficient operations.

Qualificações

• 5+ years of experience in machine learning and ML infrastructure.
• Hands-on production experience with ML models and pipelines.
• Experience with cloud platforms and production-grade tooling.

Responsabilidades

• Deploy and operate machine learning models and services in production
• Support ML workflows across data preparation, model training, evaluation, deployment, and monitoring
• Build and maintain reliable pipelines for model development and release
• Monitor model and service performance using logs, metrics, traces, and alerts
• Identify issues such as model degradation, data drift, latency, and inference failures
• Improve model serving systems for scalability, availability, security, and cost efficiency
• Support experimentation, versioning, evaluation, and A/B testing
• Troubleshoot pipelines, APIs, and runtime issues
• Collaborate with data science and engineering teams to improve model quality
• Contribute to incident investigations and RCAs for ML operations

Conhecimentos

Machine learning

Cloud engineering

SRE

CI/CD

Containers

Terraform

LLM applications

Formação académica

Bachelor’s degree in Computer Science, Engineering, Data Science, or related field

Ferramentas

Azure

AWS

Azure Machine Learning

SageMaker

Datadog

Descrição da oferta de emprego

99x is seeking a Senior Machine Learning Engineer to build, deploy, and operate ML systems in production. You will own ML pipelines, data preparation, model deployment, and monitoring across the lifecycle, partnering with data scientists and software teams to improve reliability at scale.

The role emphasizes production engineering and cloud platforms, with a focus on scalable, observable ML services and cost-efficient operations.