Member of Technical Staff, GPU Optimization

Mirage(2 months ago)

Union Square, New York, NY, New York, NYOnsiteFull TimeSenior$200,000 - $350,000AI Research

About this role

The Member of Technical Staff, GPU Optimization at Mirage focuses on enhancing the performance of AI models in video generation through advanced GPU optimization techniques. Responsibilities include optimizing training and inference pipelines on NVIDIA GPUs, designing custom CUDA and Triton kernels, and profiling multi-GPU architectures to ensure peak performance and efficiency. This role also involves collaboration with teams to create hardware-friendly model designs and staying updated on the latest advancements in GPU and compiler technologies.

View Original Listing

Required Skills

Model Optimization
CUDA
PyTorch
Video Generation
Performance Tuning
Data Pipeline Design
GPU Architecture
Python
Profiling
Debugging

+6 more

Qualifications

Bachelor's degree in Computer Science, Electrical/Computer Engineering, or equivalent practical experience
3+ years of hands-on experience writing and optimizing CUDA kernels for production ML workloads
Advanced degree (MS/PhD) in Computer Science, Electrical/Computer Engineering, or related field

About Mirage

mirage.app

Mirage is a pioneering company redefining video generation and production through advanced AI technology. Based in New York City, Mirage develops innovative tools like the Captions app and Mirage Studio, which simplify the creation of short-form videos, making them accessible and scalable for users. The company's focus on hyperrealistic actors and emotive scripts empowers brands and creators to engage audiences effectively. Co-founded by Gaurav Misra and Dwight Churchill, Mirage aims to revolutionize the future of video content production.