Machine Learning Engineer – Earth Observation AIKO

Location: Sant'Ambrogio di Torino

Overview
Joining AIKO means becoming part of a young, talented team dedicated to delivering high-quality work while maintaining a healthy work-life balance. We believe in trust, responsibility, and flexibility, offering a supportive environment where you can thrive.
Our team enjoys collaborating in our Torino office, working from home when desired, and taking time off when needed. Don’t miss the chance to revolutionize the future with us!
We are seeking a Machine Learning Engineer to join our growing and dynamic team. As a key contributor, you will play a crucial role in developing, implementing, and maintaining machine learning models, with a focus on computer vision and image processing for embedded systems. Your work will be instrumental in solving complexproblems and driving innovation in earth observation and AI-powered systems.
You will collaborate closely with a dedicated Machine Learning team, tackling challenging projects involving data analysis and information extraction for real-world applications. With a focus on deploying deep learning models within hardware-embedded environments, your efforts will help build state-of-the-art AI integration for autonomous operations in the field of Earth Observation. You will also be pivotal in implementing modern MLOps approaches to streamline our development and deployment processes.
Additionally, you will contribute to product development, working closely with cross‑functional teams to ensure that AI and ML solutions are aligned with user needs, product requirements, and overall system design. Your insights will help translate complex technical capabilities into practical, user‑focused products that advance our mission in Earth Observation technology.
We value smart, motivated, and collaborative engineers who love solving problems and making a difference. Aerospace experience is not required—what matters most is your passion for technology, your drive to innovate, and your eagerness to contribute to cutting‑edge solutions in the future of space missions and beyond.
Tasks

Lead the development and deployment of machine learning models, with a focus on computer vision and image processing, ensuring seamless integration into hardware‑embedded systems.
Design, implement, and maintain robust MLOps pipelines using tools such as Git, MLFlow, and Kubernetes to streamline model deployment and management in production environments.
Collaborate with cross‑functional teams, including software engineers, data scientists, and hardware specialists, to develop and optimize ML applications tailored for embedded systems.
Utilize Python, C++, and relevant ML libraries (e.g., PyTorch, Tensor Flow) to develop, train, and deploy deep learning models, emphasizing high performance and reliability.
Manage and handle large datasets, ensuring efficient data preprocessing and analysis, storage, and access for ML model training and evaluation.
Contribute to product design process, providing technical insights and guidance to ensure ML solutions align with user needs and product goals.
Continuously improve model accuracy and performance, applying best practices in software quality, version control, and testing.
Disseminate results and insights effectively through internal presentations, documentation, and external publications, showcasing the impact of your work.
Foster a culture of continuous improvement, driving innovation, and advocating for new methodologies and tools that enhance the company’s capabilities.

Requirements

Master’s degree in Computer Science, Engineering, Mathematics, or a related field.
Proven experience in machine learning with 3+ years in the role, showcasing a strong portfolio of expertise in developing deep neural networks, computer vision, and image processing.
Proven experience working in product development teams, contributing to collaborative design, prototyping, and deployment of ML‑based products.
Proficiency in Python, with additional skills in C++ considered a plus.
Solid understanding of MLOps principles and hands‑on experience deploying models in production using tools like Git Lab, MLFlow, and Kubernetes.
Strong statistical and analytical skills, with a…