ML Data Engineer - Object Detection & Active Learning (m/f/d)

Permanent employee, Full-time · Toulouse

Your mission
  • Design and maintain scalable pipelines to ingest and organize time-series camera and sensor data (e.g., RGB, IR, acoustic)
  • Own and improve datasets for object detection and classification tasks
  • Design and run active learning loops to select high-value samples
  • Write robust preprocessing pipelines (Python, NumPy, Pandas, Albumentations)
  • Manage labeling workflows, quality assurance, and data versioning
  • Collaborate with ML Engineers to fine-tune and evaluate model performance
  • Analyze model weaknesses and uncover actionable data insights
  • Create tools to visualize, audit, and analyze dataset quality, diversity, and model performance gaps
Your profile
  • Strong experience with Python and data processing frameworks (e.g., Pandas, NumPy)
  • Familiarity with ETL/ELT pipelines for ingesting, transforming, and structuring large volumes of sensor and video data
  • Experience with data orchestration and lifecycle management in machine learning workflows (especially video and sensor data)
  • Understanding of object detection pipelines (e.g. Detectron2, MMDetection)
  • Experience with active learning, uncertainty sampling, or semi-supervised workflows
  • Familiarity with data annotation tools (CVAT, Label Studio, etc.)
  • Solid understanding of model evaluation metrics (IoU, precision-recall, confusion matrix)
  • Comfortable with databases (SQL/NoSQL) file systems, and managing large image datasets
  • Ability to work cross-functionally with perception, deployment, and robotics engineers
Nice to have
  • Experience with cloud storage systems and MLOps pipelines (e.g., AWS S3, ClearML, MLFlow, Weights & Biases)
  • Familiarity with ROS or robotics data formats (e.g., bag files, TF trees, sensor_msgs), Docker, or embedded ML
  • Prior work with drone or robotics sensor datasets, including camera, IR, LiDAR, or audio
Meta
  • Outside of the box creativity, conceptional & systematic design thinking, disciplined execution
  • Servant leader mindset, placing team success over ego
  • Highest moral standards and work ethic
  • We value extra-curricular responsibilities and achievements in your biography
  • Intrinsic motivation, willing to go the extra mile, attention to detail
  • Fluent in English
  • Nationality of a NATO member nation or close ally is a must
  • Successful candidates will be required to obtain security clearance


Why us?
Join us to shape the future of AI-driven defense!

Do you feel that you fit the description, but don't think you fulfill all the criteria 100%? Apply to us anyway.   
We look forward to receiving your detailed application via our online form.  

The world is changing. Exponential technologies are enabling new types of security threats. We are committed to staying ahead by building nimble, scalable, and cost-effective defences. We are looking for passionate developers who are eager to create exceptional products, safeguard our freedom, and strengthen the resilience of democracies.
About us
We are a defence-tech start-up specializing in machine vision solutions. If you have a passion for cutting-edge innovation, and drive to use your skills to create next generation solutions, this is an opportunity for you!

What we do: We are developing solutions that enable computers and sensors to collaborate as teams, working together to address emerging security challenges. Our primary mission is to defend against AI-powered asymmetric threats at scale, such as drone swarms and other UXVs.

Who we are: Based in Munich, Berlin and Bordeaux/Toulouse we are rapidly expanding across Europe with plans to open more office hubs soon. We embrace a hybrid work culture - valuing the collaborations that happens in the office, while also empowering our team members to work remotely with responsibility and autonomy. 


 



Your application!
We appreciate your interest in Autonomous Teaming Solutions ATS GmbH. Please fill in the following short form. 
Uploading document. Please wait.
Please add all mandatory information with a * to send your application.