🛠 Tech Stack

💼 About This Role

You'll work across the entire vLLM stack, from low-level GPU kernels to high-level distributed systems. Your work will directly impact how the world runs AI inference by optimizing serving performance at global scale.

🎯 What You'll Do

• Optimize CUDA kernels and GPU memory management
• Design distributed orchestration for inference at scale
• Implement new model architectures in vLLM
• Build cloud automation and monitoring infrastructure

📋 Requirements

• Bachelor's degree in CS or equivalent experience
• Deep expertise in systems, GPU, distributed systems, or ML infra
• Strong track record of shipping high-impact work in complex environments
• Proficiency in at least two: CUDA, Rust/Go/C++, Python/PyTorch, K8s

✨ Nice to Have

• Contributions to vLLM or major open-source ML projects
• Experience with multiple accelerator platforms (NVIDIA, AMD, TPU, Intel)
• Knowledge of quantization or compiler technologies

🎁 Benefits & Perks

• 💵 Competitive salary + equity
• 🏥 Health coverage (location-dependent)
• 🌍 Fully remote work with global flexibility
• 🛂 Visa sponsorship case-by-case