2027 Internship Simulation Engineer, Neural Rendering

The role

You will research, implement, and benchmark neural rendering methods to generate realistic construction-site imagery. You will integrate these outputs into the simulation pipeline to help perception and planning teams train and test autonomy.

What you will do

• Research, implement, and benchmark neural rendering methods for generating realistic construction-site imagery
• Train models on real-world site data and evaluate visual fidelity, temporal consistency, and render speed
• Integrate neural rendering outputs into the simulation pipeline
• Build evaluation metrics and tooling to quantify how well rendered scenes match real fleet data
• Identify and address failure modes like dynamic objects, deformable terrain, dust, and harsh lighting
• Document findings, limitations, and recommendations on replacing traditional sim assets

Required qualifications

• Currently pursuing a BS, MS, or PhD in computer science, computer graphics, robotics, or a related field or bringing equivalent research or industry experience
• Strong Python and hands-on experience with PyTorch (or equivalent)
• Solid understanding of 3D graphics fundamentals: rendering pipelines, scene representations, camera models, and coordinate systems
• Familiarity with neural scene representations (NeRF, Gaussian splatting, neural radiance fields, or related methods)
• Comfort with real-world data

Nice to have

• Published work or substantial project experience in neural rendering, novel view synthesis, or differentiable rendering
• Experience with simulation engines (Unreal, Unity, NVIDIA Isaac Sim, or similar)
• Background in autonomous vehicle simulation or synthetic data generation
• Familiarity with C++ and GPU programming (CUDA, OpenGL, Vulkan)

About the company

Bedrock retrofits heavy equipment like excavators to be autonomous for use on real job sites. The team includes veterans from Waymo, Segment, and Uber Freight.