Senior Rendering Engineer — Unreal & GPU Synthetic Data

World Labs Inc.; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Health, dental, and vision benefits

Flexible PTO

Parental leave

Relocation support

Job summary

World Labs is seeking a Senior/Staff Rendering Systems Engineer to build high-throughput, Unreal Engine–based rendering systems for synthetic data generation in San Francisco. You will own low-level rendering and GPU performance across cloud GPU fleets, profiling workloads and implementing production-quality C++ and CUDA within Unreal Engine.

You will collaborate with infrastructure and data teams to scale distributed execution and integrate the renderer with internal pipelines.

Qualifications

• Mastery in low-level Unreal rendering architecture and GPU programming.
• Experience with distributed multi-GPU compute is valued; core graphics performance engineering is required.
• Proficiency in C++, CUDA, Python (and possibly Rust) with Vulkan implementation experience.

Responsibilities

• Modify Unreal Engine’s renderer to support run-independent worlds across GPUs and build cloud job orchestration.
• Maximize throughput and GPU efficiency via custom parallelization and caching strategies.
• Integrate rendering with internal toolchains and data pipelines.
• Perform profiling and roofline analysis to resolve compute and I/O bottlenecks.
• Collaborate with research teams to accelerate iteration and system robustness at scale.

Skills

Unreal rendering

GPU programming

C++

CUDA

Python

Rust

shader pipelines

Vulkan

Tools

Unreal Engine

CUDA

NCCL

Vulkan

Job description

World Labs is seeking a Senior/Staff Rendering Systems Engineer to build high-throughput, Unreal Engine–based rendering systems for synthetic data generation in San Francisco. You will own low-level rendering and GPU performance across cloud GPU fleets, profiling workloads and implementing production-quality C++ and CUDA within Unreal Engine.

You will collaborate with infrastructure and data teams to scale distributed execution and integrate the renderer with internal pipelines.