Senior Data Scientist – Python, ML & Signal-Processing

About DATATRONiQ

DATATRONiQ is a deep-tech startup from Germany for Industrial IoT and Edge AI. As a Senior Data Scientist with us, you will train machine learning models based on real machine and sensor data – worldwide, from medium-sized manufacturers to DAX corporations. Anomaly detection, predictive maintenance, and real-time quality monitoring. The data is real, the machines are in ongoing production, and your models will help decide whether a plant is running as planned or has an unplanned downtime. If you prefer seeing models in productive use rather than optimizing them in notebooks, then get in touch with us.

About the Role

You will be responsible for the entire data science lifecycle – from exploration, feature engineering, and model training to deployment and validation, depending on the customer situation on edge gateway, on-prem server, or in the cloud. The time series come from real industrial controls via OPC-UA and MQTT; feature engineering here means signal processing on noisy sensor data, not shuffling prepared table columns. Your models will be quantized, exported to ONNX, and run directly where production needs them – with all the consequences this has for model choice, latency, and memory consumption.

Your stack: Python, PyTorch or scikit-learn, ONNX for edge deployment, and the common MLOps tools for versioning and reproducibility.

We work in a small, closely coordinated team. Code reviews and pair programming are a regular part of everyday life. On Fridays, we show each other interesting web finds and new tools in our Show-and-Tell sessions. As a Data Scientist, you will work closely with Data Engineers and Backend Developers: You build the models, they build the pipelines, and together we bring both into production.

What are your tasks?

• You train ML models for anomaly detection, predictive maintenance, and quality monitoring and validate them on real production data and time series from industrial controls.
• You perform feature engineering on noisy sensor and machine signals (OPC-UA, MQTT, MES exports), including signal processing and filtering.
• You deploy models where the customer needs them – edge gateway, on-prem server, or cloud: quantization, ONNX export, partly with limited CPU and RAM resources, tuning and monitoring in the field.
• You work closely with Data Engineers and Backend Developers to ensure models run reliably in our production pipelines – not as prototypes in notebooks.
• You measure models not only by their F1 or AUC scores, but by what they actually achieve in production: fewer unplanned downtimes, higher throughput, fewer errors.
• You actively participate in product roadmaps and technical decisions – we expect opinions, not just ticket processing.

What should you bring?

• Completed degree in Data Science, Computer Science, Mathematics, Physics, or a related field.
• At least three years of very practical experience with Python, common ML frameworks (PyTorch, scikit-learn, etc.), and model deployment in production environments.
• Experience with time series analysis and signal processing – we don't expect PhD level, but you know why a naive MLP fails on noisy industrial signals.
• Basic knowledge of MLOps: versioning of models and data, reproducible pipelines, tests for ML code.
• Very good English skills, both written and spoken.
• You can justify technical decisions and represent them within the team – even against a majority, if you have strong arguments.
• Bonus: Experience with edge deployment (ONNX, TensorRT, quantization), industrial protocols (OPC-UA, MQTT), or LLMs for chat and agentic tasks.

What awaits you?

• Real end-to-end responsibility: from the conception of data acquisition in production through the pipeline to model inference – on edge gateway, on-prem server, or in the cloud.
• The team decides on architecture, tooling, and model strategy themselves.
• Agentic tools in everyday life: Codex, Claude Code, and new development practices – we try things out early and use what works.
• Predominantly on-site in Stuttgart, Ulm, or Berlin – Industrial IoT projects for customers worldwide, from medium-sized manufacturers to DAX corporations, on real production data.

Have we sparked your interest?

At DATATRONiQ, you are not a small cog in the machine; you shape things and bring your ideas. You will have the unique opportunity to work on a product that has the potential to have a significant impact in the industrial manufacturing sector. If you want to use your skills to solve challenging problems and actively contribute to our company, then get in touch with us!

Contact us at work@datatroniq.com or visit us at https://datatroniq.com/de/karriere. We look forward to your application!

We ask recruitment agencies and headhunters to refrain from contacting us.

Send your application to: work@datatroniq.com