🛠 Tech Stack

💼 About This Role

You'll lead the development of the next-generation AI deployment software for our AI compute engine. You'll optimize across hardware-software co-design and build scalable deliverables in a tight development window. You'll collaborate with system software experts and hardware experts to shape the future of generative AI.

🎯 What You'll Do

• Develop and maintain AI deployment software stack
• Optimize hardware-software co-design trade-offs
• Build and scale deployment infrastructure
• Collaborate with ML, compiler, and hardware teams

📋 Requirements

• BS with 12+ years or MS with 6+ years industry experience
• Strong grasp of system software and computer architecture
• Proficient in C/C++/Python in Linux
• Experience with distributed high-performance software

✨ Nice to Have

• MS or PhD in CS or EE
• Experience with inference servers like TensorRT-LLM, vLLM
• Experience with deep learning frameworks like PyTorch, TensorFlow

🎁 Benefits & Perks

• 💰 Equity included
• 💰 Bonus eligible
• 🏢 Hybrid work - 3 days onsite in Santa Clara