You want to help build Europe's resilience. You want to protect people and critical infrastructure – ultimately saving the lives of thousands.
You want to work at the frontier of high‑performance autonomous systems.
Join us at CDDS to bring next‑generation control, guidance, and state‑estimation algorithms into high-speed kinetic interceptor drones.
Your Mission
We are looking for a Senior Vision & Perception Engineer to architect and optimise our low-latency vision pipeline running on NVIDIA Jetson platforms. You will develop, tune, and extend DeepStream-based pipelines in C++, integrate differential-imaging workflows, and ensure end‑to‑end real‑time performance.
You will collaborate with robotics, control, and embedded engineers and build the perception backbone that enables high-speed interception.
Tasks
Core Responsibilities
- Implement and optimize vision pipelines in C++ for low-latency object detection and tracking
- Develop high-speed detection and tracking algorithms on Jetson platforms
- Optimise TensorRT inference performance
- Profile and tune performance down to kernel-level bottlenecks
- Maintain GPU-accelerated development containers and CI pipelines
Requirements
Your Profile
- MSc/PhD in Computer Vision, Robotics, CS, or similar
- Expert knowledge in DeepStream, GStreamer, and low-level video pipelines
- Strong C++ skills and experience with CUDA, TensorRT, or Jetson optimisation
- Strong background in modern detection models (YOLO, EfficientDet, etc.)
- Experience with ROS2 and multi-process robotic systems
- Comfortable with rapid field-testing cycles and high‑ownership environments
Benefits
Why CDDS
- Direct impact on a mission‑critical technology shaping Europe’s security landscape
- Fast‑moving startup environment with high ownership
- Work with a highly technical, ambitious, and hands‑on team
- Real‑world testing, deployments, and customer demonstrations
- Attractive compensation
Details
Location: Schlieren (Zürich), on‑site
Start date: ASAP
Environment: High‑impact deep‑tech startup working on real deployments