ML Data Engineer (m/f/d) - Sensor Data & Pipelines

Autonomous Teaming; München; Vor Ort; EUR 90.000 - 130.000; Vollzeit

Benefits dieser Stelle

International team

Career growth

State-of-the-art technologies

Continuous development

Team events

Zusammenfassung

Autonomous Teaming in Germany is seeking an ML data engineer to own object detection datasets within our perception stack. You will collaborate with ML, perception and robotics teams to transform raw sensor data into high-quality, production-ready data.

You will manage end-to-end data lifecycle: collection, labeling, QA, and continuous improvements, building pipelines and internal tools. This role sits in Munich with a fast‑moving, collaborative culture.

Qualifikationen

• Proven experience with Python and data processing tools (Pandas, NumPy) for large datasets.
• Hands-on in designing and maintaining ETL/ELT pipelines for video and sensor data.
• Experience with ML data lifecycle, versioning, and reproducibility.
• Knowledge of object detection pipelines and evaluation metrics (IoU, mAP).
• Familiarity with labeling platforms and QA processes.

Aufgaben

• Design and maintain scalable pipelines to ingest and preprocess large volumes of time-series data from cameras and sensors.
• Own and improve object detection datasets for quality and diversity.
• Build active learning loops connecting model performance with data improvements.
• Manage labeling workflows end-to-end, including tooling and QA validation.
• Collaborate with ML engineers to translate weaknesses into dataset improvements.
• Plan data collection campaigns to acquire high-value real-world data.
• Create internal tools and dashboards to analyze dataset quality and performance gaps.

Kenntnisse

Python

ETL/ELT pipelines

Data processing (Pandas, NumPy)

Dataset management

Object detection pipelines (Detectron2

Active learning

Data annotation platforms (CVAT, Label

SQL/NoSQL databases

Cross-functional collaboration

English, German

German/French as plus

Tools

Detectron2

MMDetection

COCO format

CVAT

Label Studio

Docker

ROS

Jobbeschreibung

What we offer

• Work in an international, agile team creating the future of autonomous systems
• Grow your career in a expanding and ambitious engineering team
• Build innovative products using state-of-the-art technologies in AI, robotics, and autonomy
• Benefit from a steep learning curve and continuous development
• Enjoy team events and a strong, collaborative culture

Your mission

This role sits at the core of our perception systems, owning the data that directly drives model performance in real-world environments. You will work closely with ML, perception, and robotics teams, focusing on building, curating, and continuously improving datasets behind object detection — turning raw sensor data into reliable, high-performing systems.

You will take end-to-end ownership of the ML data lifecycle, from data collection and ingestion to labeling, quality assurance, and continuous dataset improvement, ensuring data is representative, high-quality, and production-ready.

What You'll Do

• Design and maintain scalable pipelines to ingest, organize, and preprocess large volumes of time-series camera and multi-sensor data (RGB, IR, thermal, depth, IMU)
• Own and continuously improve object detection datasets, ensuring quality, diversity, and statistical representativeness
• Build and operate active learning loops, connecting model performance with data selection and improvement
• Manage labeling workflows end-to-end, including tooling, QA validation, consistency checks, and coordination of annotation efforts
• Collaborate with ML Engineers to evaluate models and translate weaknesses, bias, and drift into actionable dataset improvements
• Plan and execute data collection campaigns (e.g. field recordings, drone/video capture) to acquire high-value real-world data
• Create internal tools and dashboards to analyze dataset quality, distributions, and performance gaps

Your profile

• Strong experience in Python and data processing frameworks (Pandas, NumPy, vectorized operations, multiprocessing).
• Hands‑on experience building ETL/ELT pipelines for ingesting, transforming, and structuring large video and sensor datasets.
• Experience with data orchestration and lifecycle management for ML and computer vision workflows, including dataset versioning and reproducibility.
• Solid understanding of object detection pipelines (Detectron2, MMDetection, COCO format, bounding‑box standards).
• Experience with active learning, uncertainty sampling, or semi‑supervised dataset workflows.
• Familiarity with data annotation platforms (CVAT, Label Studio) and automated QA/consistency checks.
• Strong grasp of evaluation metrics for object detection (IoU, mAP, precision‑recall curves, class‑wise metrics).
• Comfortable with databases (SQL/NoSQL), file systems, and the management of large‑scale image, video, and sensor datasets.
• Ability to work cross‑functionally with perception, deployment, robotics, and data infrastructure teams.
• Fluent in English, German and/or French are a plus.

Nice to have

• Experience with cloud storage and MLOps tools (AWS S3, MinIO, ClearML, MLFlow, Weights & Biases).
• Familiarity with ROS / robotics data formats (bag files, TF trees, sensor_msgs), Docker, or embedded ML workflows.
• Prior work with robotics, drones, or multi‑sensor perception systems, including IR, LiDAR, radar, or audio datasets.

What else

• Outside‑the‑box creativity with a blend of conceptual and systematic design thinking.
• High intrinsic motivation, attention to detail, and strong problem‑solving mindset.
• Structured, methodical, and reliable execution, even under uncertainty.
• Humble, collaborative, and mission‑driven — values collective success over ego.
• High ethical standards and disciplined work ethic.
• Extra‑curricular achievements, leadership, or unique projects are a plus.
• NATO‑aligned nationality or close ally citizenship is required.

Why us?

Join us to shape the future of AI‑driven defense!

About Us

The world is changing. Exponential technologies are enabling new types of security threats. ATS is committed to staying ahead by building nimble, scalable, and cost‑effective defences. We are looking for passionate team members who are eager to create exceptional products, safeguard our freedom, and strengthen the resilience of democracies.

Who we are

Autonomous Teaming is a defence‑tech start‑up specializing in machine vision solutions. Driven by cutting‑edge innovation, our team works on next‑generation technologies designed to meet rapidly evolving security challenges.

What we do

We develop systems that enable computers and sensors to operate as coordinated teams, collaborating in real time to counter AI‑powered asymmetric threats at scale — including drone swarms and other UXVs. Our mission is to build resilient, intelligent defence capabilities that perform reliably in the most demanding environments.

How we work

We value close, in‑person collaboration as the foundation for building complex, high‑impact technology, while maintaining flexibility aligned to role and team needs. Our culture is built on ownership, responsibility, and trust — with a shared commitment to growing and building together.

Where we are

Based in Munich, Berlin, and Toulouse, we are expanding rapidly across Europe with plans to open additional office hubs.