About Us
STARK is a defense technology company revolutionizing the way autonomous systems are deployed across multiple domains. We design, develop and manufacture high-performance unmanned vehicles that are software-defined, mass-scalable, and cost effective – giving NATO and its allies a decisive edge in the most contested environments. We’re focused on delivering deployable, high-performance systems—not future promises. In a time of rising threats, STARK is bolstering the technological edge of NATO Allies and their Partners to deter aggression and defend Europe—today.
About the team
Minerva is STARK's command and control software — the brain that connects operators to autonomous systems across multiple domains in real time. The Minerva team is a small, senior software group based in Berlin and Munich, working directly with our systems and hardware teams to build mission-critical C2 capabilities deployed in active operational environments. We move fast, ship real software, and operate under constraints most engineers never encounter — low-bandwidth networks, air-gapped devices, high-stakes decision loops. There is no room for abstraction for its own sake. Everything we build ends up in the hands of real operators in the field.
Your mission
As a Robotics Engineer with a focus on embedded perception systems, you will play a critical role in enabling real-time autonomy onboard next-generation UAV platforms. You will work directly with camera data pipelines, ROS2-based systems, and embedded compute platforms to build robust, efficient, and scalable perception functionality.
You will contribute as a highly skilled individual contributor—hands-on with the system—bridging diverse codebases and enabling data flows across native ROS2 nodes, legacy frameworks, and containerized third-party modules. Your work will be essential to ensuring that our autonomous systems operate reliably in real-world, resource-constrained environments.
Responsibilities
Develop and integrate real-time perception pipelines on embedded platforms such as the Jetson Nano NX.
Migrate legacy monolithic systems to ROS2, refactoring and modularizing components for better scalability and maintainability.
Enable and optimize image data access across native and containerized components (e.g., Dockerized ROS2 processes).
Design and implement low-level camera and sensor drivers for real-time vision acquisition.
Collaborate with AI, controls, and hardware teams to ensure tight integration between perception and other onboard subsystems.
Profile and debug system performance under embedded constraints (compute, thermal, bandwidth), ensuring stability and robustness in field deployments.
Contribute to system-level architecture discussions with a focus on communication reliability and modularity.
Qualifications
Bachelor’s or Master’s degree in Engineering or a related technical field.
Strong experience with ROS2, including real-world deployment and integration of perception modules.
Proficient in Python and C++ for embedded and robotics development.
Solid background in robotics, autonomous systems, embedded development, or aerospace applications.
Familiarity with embedded Linux platforms, particularly NVIDIA Jetson devices.
Experience integrating containerized processes (e.g., Docker) into onboard robotic systems.
Ability to navigate and coordinate between different frameworks (ROS2, legacy/custom codebases, third-party modules).
Strong problem-solving and debugging skills, especially in real-time or resource-constrained environments.
Effective communicator and team player in multidisciplinary engineering teams.
Self-driven, organized, and adaptable to fast-paced development cycles.
Willingness to travel occasionally for field testing and deployment.
