Senior Data Scientist – Python, ML & Signal Processing

About DATATRONiQ

DATATRONiQ is a German deep-tech startup focused on industrial IoT and edge AI. In this role, you will build machine learning solutions using real machine and sensor data from live production environments, serving customers from mid-sized manufacturers to large enterprise groups. The work centers on anomaly detection, predictive maintenance, and real-time quality monitoring, with models that directly influence uptime and production stability.

Role overview

As a Senior Data Scientist, you will own the full data science lifecycle end to end: exploration, feature engineering, model training, deployment, and validation. Depending on the customer setup, solutions may run on edge gateways, on-premise servers, or in the cloud. The data comes from real industrial control systems via OPC-UA and MQTT, so feature engineering involves signal processing on noisy sensor data rather than simply working with cleaned tabular datasets. Your models will be quantized, exported to ONNX, and deployed where production actually needs them, which means model choice, latency, and memory efficiency matter.

Your core stack includes Python, PyTorch or scikit-learn, ONNX for edge deployment, and standard MLOps tools for version control and reproducibility. The company works as a small, closely aligned team, with code reviews and pair programming as part of everyday collaboration. Fridays include show-and-tell sessions where the team shares interesting web discoveries and new tools. You will collaborate closely with data engineers and backend developers to move models from prototype into production pipelines.

Responsibilities

• Develop, train, and validate ML models for anomaly detection, predictive maintenance, and quality monitoring using real production data and industrial time-series signals.
• Perform feature engineering on noisy machine and sensor signals, including signal processing and filtering of data from OPC-UA, MQTT, and MES exports.
• Deploy models to the appropriate environment for the customer, whether edge gateway, on-premise server, or cloud, and handle quantization, ONNX export, tuning, monitoring, and resource constraints.
• Work closely with data engineers and backend developers to ensure models run reliably in production pipelines instead of remaining notebook prototypes.
• Evaluate models based on real-world operational impact, such as reducing unplanned downtime, improving throughput, and lowering defect rates, not just by F1 or AUC metrics.
• Contribute actively to product roadmap discussions and technical decisions, bringing viewpoints and initiative rather than only executing assigned tickets.

Requirements

• A completed degree in Data Science, Computer Science, Mathematics, Physics, or a closely related field.
• At least 3 years of hands-on experience with Python, common ML frameworks such as PyTorch and scikit-learn, and deployment of models in production environments.
• Practical experience with time-series analysis and signal processing, with enough understanding to know why a simple MLP can fail on noisy industrial signals.
• Basic MLOps knowledge, including model and data versioning, reproducible pipelines, and testing for ML code.
• Strong English communication skills, both spoken and written.
• Ability to justify technical decisions and defend them within a team when your reasoning is sound.
• Nice-to-have experience with edge deployment tools such as ONNX, TensorRT, and quantization, industrial protocols like OPC-UA and MQTT, or LLMs for chat and agentic tasks.

What to expect

• True end-to-end ownership, from designing data capture in production through the pipeline and model inference on edge gateways, on-premise servers, or in the cloud.
• The team makes its own decisions on architecture, tooling, and test coverage.
• Access to agentic tools in everyday work, including Codex, Claude Code, and newer development practices that are adopted early when they prove useful.
• Mostly on-site work in Stuttgart, Ulm, or Berlin, on industrial IoT projects for global customers ranging from mid-sized manufacturers to DAX-listed enterprises.

Additional information

You will not be a small cog in the machine here; the role is intended for someone who wants to shape the product and contribute ideas. The company offers the chance to work on a product with the potential to make a significant impact in industrial manufacturing. Interested candidates are invited to get in touch by email at work@datatroniq.com.

Application note

Recruitment agencies and headhunters are asked not to make contact.