🛠 Tech Stack

💼 About This Role

You'll join an elite AI lab pioneering general-purpose world models and their real-time inference. Your core impact will be optimizing model performance to scale to hundreds of thousands of users while minimizing compute cost. You'll partner with top researchers and have significant autonomy on technical decisions.

🎯 What You'll Do

• Optimize models for real-time inference at scale
• Design distributed training strategies on large GPU clusters
• Develop tools to identify performance bottlenecks
• Pioneer frameworks to enhance performance metrics

📋 Requirements

• 8+ years of software engineering experience
• Deep insight into modern ML architectures and performance optimization
• Proficiency with PyTorch (or TF/JAX) and Triton
• Experience with NVIDIA GPU ecosystems and optimization stacks

✨ Nice to Have

• Track record of owning projects end to end
• Problem-solving mindset with ability to acquire new skills

🎁 Benefits & Perks

• 💻 Latest-generation GPUs to work with
• 🎯 Significant autonomy in technical decisions