🛠 Tech Stack

💼 About This Role

You'll collaborate with autonomy engineers to scale self-driving systems using an AI-first approach, expanding model deployment pipelines to new GPUs and embedded systems. Your work will directly optimize inference on autonomous trucks.

🎯 What You'll Do

• Optimize models using TensorRT and modelopt for inference on GPUs
• Create and benchmark custom CUDA kernels for inference
• Profile runtime and memory to identify performance bottlenecks
• Expand deployment pipeline to new platforms like Jetson or Thor

📋 Requirements

• 6+ years industry experience in CS, Robotics, or related field
• Proficiency in Python, C++, or Rust
• Experience with deep learning frameworks like PyTorch
• Skilled in profiling using PyTorch Profiler and NVIDIA Nsight

✨ Nice to Have

• Experience with model compilation and TensorRT
• Implementing custom CUDA kernels
• Experience with Bazel build systems

🎁 Benefits & Perks

• 🏖️ Unlimited PTO
• 🏥 Health insurance
• 📈 Stock options
• 💻 Remote work

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter Screen· 30 min
2. 2Technical Interview· 60 min
3. 3On-site Interview· 3 hours