World Labs

Performance Engineer (Inference, Training & GPU)

San Francisco · Senior

Sponsorship not specified$200k-$300kDetected 5 days ago

PythonGoRustC++Distributed SystemsMachine LearningPyTorchExcelSystems EngineeringResearchCommunication

About the role

We are looking for a Performance Engineer to make World Labs' models train and serve as fast as the hardware allows.
Running large generative world models at scale is a novel systems problem.
You will find the bottlenecks - in kernels, in the serving path, in the training loop, in how we use our GPUs - and eliminate them.

Optimize inference and serving end to end - latency, throughput, batching, caching, and scheduling - to serve our models efficiently at production scale.
drive kernel fusion, memory- and bandwidth-bound optimization, and low-precision (FP8/INT8) execution.
Optimize training throughput and GPU utilization: parallelism strategies, communication/compute overlap, mixed precision, and eliminating pipeline stalls.
Build performance models, profiling workflows, and observability that make throughput, latency, cost, utilization, and their tradeoffs legible across the stack.
Partner with researchers to productionize models for serving and to make experiments run faster and more reliably.
We're building something bigger than any one person.

Working knowledge of ML framework internals (PyTorch and/or JAX
Strong proficiency in Python, with the ability to drop into C++/CUDA (and Rust or Go) as the work demands.
You should excel at the fundamentals below - we index on inference, serving, GPU optimization, and training performance.
Distributed-systems breadth is welcome, but secondary.

Experience at an AI lab or ML-native company, optimizing systems used directly by researchers and productionizing research code.
Low-precision and numerics depth: FP8/INT8 quantization, mixed-precision, and detecting numerical regressions across hardware platforms.
Distributed systems for large-scale training and inference - collective communication (NCCL), interconnects (NVLink), model and tensor parallelism, and fault tolerance.
A strong plus, but not a substitute for the core skills above.
Experience serving generative, diffusion, video, or 3D/spatial models - not just text LLMs.
Multi-accelerator experience (GPU plus TPU or Trainium) and partnering with hardware vendors on accelerator capabilities.
Fearless Innovator: We need people who thrive on challenges and aren't afraid to tackle the impossible.
Resilient Builder: Impacting Large World Models isn't a sprint

$200-$300k base salary (good-faith estimate for San Francisco Bay Area upon hire
Total Compensation
Base salary plus equity awards
Salary History
We do not request or consider prior compensation in making offers
Cal. Lab. Code §1197.5 (Equal Pay Act)
$200-$300k base salary (good-faith estimate for San Francisco Bay Area upon hire; actual offer based on experience, skills, and qualifications)

Own numerical correctness across precision, kernel, and hardware changes - treating correctness as part of performance, not separate from it.
You should excel at the fundamentals below - we index on inference, serving, GPU optimization, and training performance. Distributed-systems breadth is welcome, but secondary.

World Labs is an equal opportunity employer.
We do not discriminate on the basis of race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability, genetic information, veteran status, or any other characteristic protected under applicable law.
We welcome all qualified applicants and are committed to providing reasonable accommodations throughout the hiring process upon request.
California Pay Transparency

This listing is sourced directly from World Labs's careers page and normalized into a canonical job model.