MLOps Engineer

This is a fully remote position, open to applicants in Greece.

📋 Description

• Develop workflows for the execution and management of model training and fine-tuning tasks.

• Ensure experiments are traceable through versioning of datasets, checkpoints, and model artifacts.

• Automate the evaluation of models and release checks, enabling teams to assess changes prior to deployment.

• Create deployment and serving workflows, including secure rollouts and rollbacks of model versions.

• Enhance GPU workload scheduling and utilization, focusing on performance and computational costs.

• Incorporate monitoring and troubleshooting tools for production machine learning systems.

• Collaborate with teams to address recurring production challenges.

• Work closely with ML and Engineering teams to ensure reproducibility of experiments and reliability in model deployment and production operations.

⛳️ Requirements

• Practical experience in building or managing infrastructure for production machine learning systems.

• Strong skills in Python and Linux.

• Ability to write maintainable code for production environments.

• Solid understanding of the machine learning lifecycle, from experimentation and evaluation to model deployment.

• Familiarity with containers, workload orchestration, CI/CD, and automation of infrastructure.

• Experience with GPU workloads and assessing performance, utilization, and costs.

• Proven experience in monitoring and troubleshooting production systems.

• Experience with large language model serving tools such as vLLM, SGLang, or NVIDIA Triton.

• Background in distributed or multi-GPU training.

• Experience with machine learning tools like MLflow, Weights & Biases, Kubeflow, or Ray.

• Experience in supporting machine learning workloads within private cloud or on-premises environments that adhere to data governance requirements.

🏝️ Benefits

• Competitive compensation package aligned with industry talent benchmarks.

• Engaging hands-on work that shapes AI capabilities for products and real-world applications.

• AI-native environment featuring challenges across model development, evaluation, and production AI systems.

• Engineering-first culture that promotes innovation.

• High level of autonomy with minimal bureaucracy.

• Opportunity to contribute to meaningful AI product development.