Software Engineer, Command Centre (Vision)

Laelaps AI is a company focused on developing intelligent software for physical security, leveraging advancements in AI, cloud computing, and hardware. Their mission is to create autonomous systems that handle dangerous and critical tasks, making the world safer and more secure. The role of a Software Engineer, Command Centre (Vision) involves working on vision-agents, a service that processes camera and robot feeds to provide reliable alerts to operators. The main responsibilities include owning the vision-agents service, which involves architecture, code quality, and performance. This includes handling streaming at scale, detection, tracking, and re-identification of objects, natural-language monitoring, evaluation, performance optimization, privacy by design, access control, and deployment. The role requires working with full-stack engineers on the operator console and API, ensuring the service runs smoothly on GPU servers at customer sites and in the cloud. To qualify for this role, candidates must have at least three years of experience building and running computer vision or ML systems in production. Strong Python skills and solid software engineering practices, including async services, testing, profiling, and clean interfaces, are essential. Experience with object detection, multi-object tracking, and re-identification across multiple cameras, as well as real-time video processing using RTSP, GStreamer, or DeepStream, is required. Additionally, candidates should have hands-on experience with model optimization and serving, including ONNX, TensorRT, quantization, and serving large models. Knowledge of Docker and Kubernetes is also necessary. Nice-to-have skills include experience with NVIDIA DeepStream or Triton Inference Server, open-vocabulary detection or segmentation models, and licence-plate recognition or access-control systems. Familiarity with privacy engineering for video, including masking, anonymization, and GDPR, is also beneficial. A background in surveillance, security, or defence systems, as well as experience with C++ for performance-critical paths, can be advantageous. Publications at top venues are a plus but not expected. The role offers a unique opportunity to work directly with PhD-level co-founders in AI, Robotics, and Physics, alongside a strong and fun founding team. The company provides a competitive equity/salary package and a culture that is serious about building but does not take itself too seriously. The location is Zurich, and the team is international, offering a ground-floor seat with real runway for career growth. What the role asks for: - 3+ years building and running computer vision or ML systems in production. - Strong Python and solid software engineering: async services, testing, profiling and clean interfaces. - Hands-on experience with object detection, multi-object tracking and re-identification across multiple cameras. - Real-time video: RTSP, GStreamer or DeepStream, hardware decoding and multi-stream pipelines. - Model optimization and serving: ONNX, TensorRT, quantization, and serving large models with vLLM or similar. - Experience building with vision-language models and evaluating them rigorously. - Docker and Kubernetes. - Nice to have: NVIDIA DeepStream or Triton Inference Server.