Senior / Staff Research Engineer, Generative AI Deployment

Highlights

• Own research-to-production path for neural models powering Waabi World simulator.
• Make diffusion and scene reconstruction models fast for closed-loop simulation.
• Build benchmarks ensuring speedups preserve simulation realism and autonomy metrics.

Ideal candidate

A production-minded ML engineer who loves turning cutting-edge generative research into fast, trustworthy systems and thrives partnering with scientists to power realistic large-scale simulation.

Requirements

• Experience reading and developing production-quality software at scale and shipping ML systems
• Experience taking models from research codebase to optimized production artifact with speedup and accuracy measurement
• Hands-on experience with TensorRT, torch.compile, torch.export, ONNX, quantization, pruning
• Experience handling models with custom CUDA operators or operations that don't export cleanly
• Experience profiling with Nsight Systems, Nsight Compute, and PyTorch profiler
• Ability to write or modify CUDA or Triton kernels
• Understanding of vision transformers, diffusion and flow-matching models, and vision foundation models
• Experience launching and debugging GPU jobs in AWS/GCP with orchestration and containers