onsite
Machine Learning Engineer - Hetzner Online GmbH
ML Engineer
Develop and deploy scalable ML models using Python, TensorFlow, and PyTorch on AWS infrastructure, ensuring high performance and reliability through containerization and orchestration.
About the role
Key Responsibilities
- Design, implement, and maintain end‑to‑end machine learning pipelines for production workloads.
- Collaborate with data scientists to translate research prototypes into scalable, production‑ready services.
- Deploy models on AWS using Docker containers and manage them with Kubernetes for high availability.
- Monitor model performance, perform drift detection, and iterate on model retraining cycles.
- Optimize inference latency and resource utilization across cloud and on‑prem environments.
Requirements
- Strong programming skills in Python and experience with TensorFlow or PyTorch.
- Hands‑on experience deploying ML models on AWS (SageMaker, ECS, EKS).
- Proficiency with containerization (Docker) and orchestration (Kubernetes).
- Solid understanding of CI/CD pipelines and automated testing for ML workflows.
- Excellent problem‑solving skills and ability to work in a fast‑paced, collaborative team.
Skills
pythonmachine learningtensorflowpytorchawsdockerkubernetes