Senior ML Infrastructure Engineer

Job title: Senior ML Infrastructure Engineer

About the Role Work with our deep learning engineers and data scientists to design, maintain, and extend the system for running deep learning experiments. You’ll own Python-based tooling and the infrastructure that powers the experimentation framework, including databases, VMs, cloud compute resources, and scheduling systems. You’ll have opportunities to propose improvements, automate repetitive tasks, and directly shape how we work.

What You'll Do

• Collaborate with DL engineers and data scientists to design, maintain, and extend our deep learning experimentation system.
• Build and maintain Python-based tooling, libraries, and services.
• Own the experimentation framework infrastructure: databases, virtual machines, cloud compute resources, scheduling systems.
• Identify and implement improvements to robustness, efficiency, and user experience of the infrastructure.
• Develop tools for better insights and control over ML experiments, including a custom experiment control and visualization website.
• Leverage CI/CD and automation to minimize repetitive tasks.
• Take ownership over parts of codebase and infrastructure; contribute ideas for continuous improvement.

What We're Looking For

• Bachelor’s or master’s degree in a technical field.
• At least 5 years of relevant work experience.
• Strong proficiency in Python with robust, clean, maintainable code.
• Experience with technologies in our stack (e.g., Ubuntu, Docker, Slurm, MongoDB, Postgres, Ansible, Prometheus, Grafana, TensorFlow, CUDA, React, FastAPI, GitHub Actions).
• Knowledge of software design and architecture patterns; able to apply them to large codebases.
• Ability to lead a project from start to finish.
• Strong communication skills in English.
• Willingness and ability to learn new tools and environments.

Nice to Have

• Experience designing and maintaining a deep learning infrastructure.
• DevOps experience and cloud providers.
• Familiarity with Python scientific computing packages (NumPy, SciPy, scikit-learn, TensorFlow).

Compensation & Benefits

• Competitive compensation package.
• 30 days of paid vacation.
• Free daily meals, drinks, and snacks at our Berlin office.
• Regular team events and a yearly retreat.
• Company-sponsored Deutschlandticket public transport.
• Hybrid work model (at least 60% on-site).