Software Engineer, Simulation (Digital Twins)

h3Our Mission /h3pAt Laelaps AI, we believe robotics is entering a transformative decade, much like the arrival of the internet. Advances in AI, cloud computing, and hardware are reshaping what autonomous systems can do. Our mission is to build the intelligent software that powers physical security in the real world - enabling robots and sensors to handle dangerous and critical tasks that humans shouldn't have to. By engineering the orchestration layer for intelligent security, we aim to create a world that is safer, more secure, and more resilient. /ppWe're a strong founding team based in Zurich, backed by visionary investors and advisors. We are engineering the future of security today! /ph3The Role /h3pYou will be the first engineer on our Simulation team.

Every site we map becomes a digital twin, built from our own lidar maps, and in it our robots see thousands of the intrusions, fires and sensor failures a real site sees once a year. Our multi-robot patrol policy was trained in simulation in under two hours on a single GPU and ran unmodified on real robots at three sites.

Your job is to make that repeatable for every site and every new skill. /ppYou will work with our Skills Orchestration engineers, who train learned skills with reinforcement learning, and with our Reliability Test Infrastructure engineer, who runs regression in the same simulator. /ph3What You'll Work On /h3ullipMap to twin: a pipeline from our lidar maps to simulation-ready digital twins: geometry, semantics, materials, sensors. /p /lilipTraining environments: RL environments for learned skills such as multi-robot patrol and search, randomised so nothing overfits one site. /p /lilipRare events: generate the scenarios real sites rarely produce: intrusions, sabotage, weather, sensor failures. /p /lilipSensor simulation: RGB, thermal and lidar realistic enough that what is learned in the twin holds on the robot. /p /lilipSim-to-real: measure the gap on real deployments and close it. /p

/lilipScale: many parallel environments on GPUs, fast enough that a new skill trains in hours. /p /li /ulh3Who We're Looking For /h3pA simulation engineer who treats the simulator as production infrastructure and measures success by what transfers to real robots. /ph3Your Background /h3ullip3+ years building robotics simulation or RL training environments. /p /lilipHands-on with Isaac Sim or Isaac Lab; MuJoCo or Gazebo also considered. /p /lilipStrong Python; C++ a plus. /p /lilip3D data: point clouds, meshes, scene formats such as USD. /p /lilipGPU-parallel simulation and reinforcement learning workflows. /p /li /ulh3Nice to Have /h3ullipLegged robots. /p /lilipPhotogrammetry, Gaussian splatting or other scene reconstruction. /p /lilipROS 2. /p /lilipThermal or lidar sensor modelling. /p /li /ulh3What We Offer /h3ullipOwnership: you are able to ship products and deliver project

end-to-end. /p /lilipMission: autonomous security that keeps people and critical sites safe, including in defence. /p /lilipCareer path: a ground-floor seat with real runway. Prove your value and you will not have barriers to grow. /p /lilipTeam: work directly with PhD-level co-founders in AI, Robotics, and Physics, alongside a strong (and fun) founding team. /p /lilipCompensation: Competitive equity/salary package /p /lilipCulture: International founding team that is serious about building but does not take itself too seriously. /p /li /ul