ZAITRA, established in 2020, is a startup with a primary emphasis on delivering tailored flight software and cutting-edge AI solutions for space missions. Our endeavours encompass projects for both the European Space Agency and commercial customers.
About the role
As a Machine Learning Engineer, you’ll design and optimize AI models for deployment on spacecraft and satellites. This entails:
- Designing, training and optimizing machine learning models for edge devices with limited computational resources.
- Preprocessing and augmenting multispectral and hyperspectral satellite imagery at various processing levels to ensure high-quality data for ML models.
- Working with computer vision algorithms for edge devices that serve either as a preprocessing step for ML models or as stand-alone solutions.
- Collaborating with hardware and software engineers to integrate AI models into embedded systems.
- Conducting research based on project needs—exploring both emerging and established methods.
- Contributing to the technical sections of ESA proposals and final project reports (e.g., for ESA or TA CR).
- Co-authoring our research papers and publications to share findings with the scientific community.
- Documenting your work and contributing to the development of internal tools and frameworks.
Required qualifications
- Solid technical background in computer science, machine learning, or a related field.
- Proven experience in training, optimizing, and deploying machine learning models (e.g., convolutional neural networks).
- Knowledge of computer vision principles and techniques, including traditional approaches and deep learning-based methods.
- Strong programming skills in Python, with knowledge of ML frameworks such as TensorFlow, PyTorch, or scikit-learn.
- Familiarity with edge AI techniques like quantization, pruning, and model compression.
- Experience with version control systems (Git), including branching, merging, and writing clear commit messages.
- Strong analytical and problem-solving skills.
- Enthusiasm for space.
What we offer
- Hybrid work (preferably with at least 3 days a week in our office).
- Flexible working hours.
- Modern offices near the center of Brno.
- Direct impact on the development and direction of products for space missions.
- Involvement in the development of solutions to be deployed in Earth’s orbit and beyond.
- 5 weeks of vacation.
- Meal vouchers.
- Team-building activities and company events.
What is nice to have
- Experience in embedded systems or optimizing AI models for constrained hardware.
- Familiarity with satellite imaging (e.g., hyperspectral, multispectral data).
- Knowledge of C++ or Rust for high-performance model implementation.
- Active contribution to open-source projects.
- Understanding of ECSS.
- Experience with model deployment frameworks (e.g., ONNX, TVM, OpenVINO, TensorRT).
- Authorship or co-authorship of published research papers in relevant domains (e.g., AI, computer vision, or remote sensing).
Interview process
- Submit your CV and short cover letter via email to jobs@zaitra.io.
- Attend a 30-minute call with the CTO and HR.
- Complete a short take-home task.
- Participate in a 60-minute technical screening, including a review of your task.
- Receive an offer.