🛠 Tech Stack

💼 About This Role

You'll build low-latency inference pipelines for on-device deployment, enabling real-time control loops in robotics. You'll design distributed inference systems on GPU clusters and push throughput with efficient resource utilization. This role combines low-level CUDA and Triton with high-level framework integration.

🎯 What You'll Do

• Build low-latency inference pipelines for on-device deployment
• Design and optimize distributed inference systems on GPU clusters
• Implement efficient low-level code (CUDA, Triton, custom kernels)
• Develop monitoring and debugging tools for reliability and determinism

📋 Requirements

• 8+ years of experience in distributed systems or ML infrastructure
• Production-grade expertise in Python and systems languages (C++/Rust/Go)
• Low-level performance mastery in CUDA and Triton
• Proven track record scaling inference workloads in cluster and on-device environments

✨ Nice to Have

• Experience with quantization and memory scheduling
• Knowledge of graph compilation techniques
• Background in robotics or real-time systems

🎁 Benefits & Perks

• 💰 Competitive Equity
• 🏖️ Unlimited PTO
• 🏥 Health Insurance