voize is hiringML Ops Engineer

🎤 Why voize? Because we’re more than just a job!

At voize, we’re revolutionizing the healthcare industry with AI: Nurses simply speak their documentation into their smartphones, and our AI automatically generates the correct entries. This saves each nurse an average of 39 minutes per day, improves the quality of documentation, and makes their daily work much more rewarding.

Voize is YCombinator-funded, already in use at over 600 senior care homes, and has grown by 100% in the last 90 days. Our customers save over 3.5 million hours annually – time spent on people instead of paperwork.

But this is just the beginning. With our self-developed voize AI, we’re transforming not only the healthcare industry, but also have the potential to create value in many other sectors – from healthcare to inspections.

As a dynamic team, we blend cutting-edge technology with social impact. And now, it’s your turn to join us!

💡 Your Mission:

If you're excited to work at the cutting edge of ML infrastructure, large-scale systems, and MLOps, then go ahead and apply! With us, you'll design and scale robust infrastructure, optimize training pipelines on real-world data, and enable our ML and Data teams to ship models and features to production every day.

🚀 Your Daily Business – No two days are alike

• Monitor, maintain, and scale our ML infrastructure—including GPU clusters, ML controllers, and cloud/on-prem resources—ensuring smooth model training and deployment at scale

• Deploy and manage hosted models for production use cases, assisted labeling, and ML-powered backend products like RAG

• Design and optimize data infrastructure systems and pipelines to process ever-growing datasets, support data exploration and annotation, and meet high reliability/performance requirements

🤝 Your Skillset – What you bring to the table

• Several years experience deploying and serving ML models in production environments, using frameworks like Triton and formats like ONNX to ensure scalable, low-latency inference

• You’ve worked with ML training infrastructure, including managing on-prem or colocation GPU clusters

• You have significant experience with ETL & Data pipelines, including stream vs. batch processing, monitoring, and DAG scheduling with tools like Airflow

• You follow best practices with Infrastructure as Code and GitOps, using tools like Terraform, Helm, or ArgoCD

• You are fluent in container orchestration with Kubernetes and Docker, ensuring smooth deployment, monitoring, and maintenance of machine learning services.

🎯 Our Success Mindset – How we work at voize

• You speak fluent German (B2 or higher) & good English to communicate effectively with our team and customers

• Resilience is one of your strengths – you see challenges as opportunities, not obstacles

• Iterative working suits you – you test, learn, and improve constantly instead of waiting for perfection

• Communication & feedback come naturally to you – you openly address issues and both give and receive constructive feedback

🌱 Growing together – what you can expect at voize

• Become a co-creator of our success with virtual stock options

• Our office is in Berlin, and we offer remote work

• We provide flexible working hours because you know best when you work most efficiently!

• Access to various learning platforms (e.g., Blinkist, Audible, etc.)

• We have an open culture and organize regular work weeks and team events to collaborate and bond

• We are a fast-growing startup, so you'll encounter various challenges, providing the perfect foundation for rapid personal growth

• Your work will make a real impact, helping alleviate the workload for healthcare professionals

• Free Germany Ticket and Urban Sports Club membership

• 30 days of vacation – plus your birthday off

✨ Ready to talk? Apply now! 🚀

We look forward to your application and can’t wait to meet you – no matter who you are or what background you have!