Simulation Engineer

As our Simulation Engineer, you'll own the layer that makes our 3D outputs genuinely useful for robot training assets and environments that are physically accurate, properly articulated, and validated to behave correctly in Isaac Sim. The core of the work is building and hardening our physics and articulation pipelines, reconstructing real environments from captured data, and ensuring everything holds up under simulation. This is a hands-on technical role at an early-stage company where your work ships directly to robotics design partners.

About Kaedim

Kaedim is an a16z-backed startup that raised $15M in our Series A to build the data infrastructure powering the next generation of robot training. Our AI pipeline turns 3D assets and real-world environments into validated, sim-ready datasets at the quality and scale robotics companies need to close the sim-to-real gap. We sit at the intersection of generative 3D, physics simulation, and physical AI, and we're just getting started. Explore what we're building at projectsim.ai

What you'll do

• Own the physics injection pipeline where you predict and validate physical properties (mass, inertia, friction, centre of mass) for 3D assets so they behave correctly under simulation
• Build and harden the articulation pipeline — segment parts, classify joints, define joint types and ranges, and export clean URDFs and USD articulation schemas
• Validate assets and environments in Isaac Sim / Isaac Lab — headless load tests, drop tests, robot interaction tests, and systematic diagnosis of collision artefacts, physics instabilities, and articulation failures
• Build the real2sim reconstruction pipeline — real environments captured via 3DGS or photogrammetry → cleaned and aligned → converted to USD via NVIDIA NuRec → validated in Isaac Sim
• Define and maintain physics benchmarks — measure outputs against ground truth and track improvements over time as the pipeline evolves
• Work on scenario generation and domain randomisation — configure variation across physics parameters, lighting, object placement, and camera setups to produce training-ready episode distributions
• Develop tooling and automation to scale the pipeline from design-partner prototype to production service
• Track the frontier — stay across advances in physical AI simulation (Isaac Lab, Genesis, VLA pre-training, Seed3D, RoboSimGS) and bring relevant work into the pipeline

What you'll bring

• Strong hands-on experience with physics-based simulation, ideally NVIDIA Isaac Sim or Isaac Lab
• Solid understanding of rigid-body dynamics, kinematics, and common simulation failure modes — instability, collision artefacts, articulation errors
• Experience working with OpenUSD and common 3D/robotics asset formats (FBX, URDF, MJCF, GLB)
• Solid grasp of 3D geometry, meshes, rigging and articulation, collision geometry, and materials
• Proficiency in Python; experience with automated ML or data pipelines is a plus
• Familiarity with Gaussian splatting or photogrammetry workflows for real-to-sim reconstruction is a meaningful plus
• Experience with other simulation platforms (MuJoCo, Genesis, Gazebo) is a plus
• Bonus: Blender, Houdini, or similar 3D DCC tooling experience
• Strong problem-solving skills and comfort collaborating closely with 3D AI researchers and ML engineers

Why Kaedim?

• Work on a genuinely hard and important problem — the data bottleneck that's limiting physical AI
• a16z-backed Series A company with offices in London, New York, San Francisco, and Singapore
• Build the data infrastructure layer that the next generation of robotics companies will train on
• Small, technical team where your work ships fast and matters

How we work

We're a small, ambitious team that moves fast and takes real ownership of our work. Everyone is in the office five days a week, typically 9 to 9, because we're genuinely excited about what we're building and want to see it ship. If you want to work alongside people who care deeply, move quickly, and feel the direct impact of their work every day, we'd love to hear from you. You can read more about what it's like to be part of the team at github.com/Kaedim/working-at-kaedim.