🛠 Tech Stack

💼 About This Role

You'll own the accelerated compute layer for a home robotics platform, ensuring efficient GPU utilization for model inference, SLAM, and more. You'll work cross-functionally to meet real-time system requirements. This role offers the chance to shape GPU scheduling and camera pipelines for a generalized robot platform.

🎯 What You'll Do

• Reduce GPU kernel launch overheads and swap models efficiently
• Arbitrate GPU access across concurrent users with predictable latency
• Drive low-latency camera frame transfer into GPU memory
• Build efficient CPU↔GPU data movement with zero-copy paths

📋 Requirements

• 2+ years developing GPU systems software
• Strong proficiency in CUDA and C++, C, or Rust
• Solid understanding of GPU architecture and time-slicing tradeoffs
• Hands-on experience with CUDA Graphs and CUDA IPC

✨ Nice to Have

• Contributions to CUDA libraries
• Experience with camera pipeline integration and NVDEC/NVENC
• Experience optimizing model inference on embedded GPU platforms (e.g., Jetson)

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter Call· 30 min
2. 2Technical Screen· 60 min
3. 3On-site Interviews· 4 hours