Distillation Lead
Core
Lead strategy and execution for model distillation and compression across Waabi's AI stack to enable efficient deployment of large-scale neural networks in autonomous vehicles and simulations.
Role type
Senior IC Distillation Lead (Physical AI)
Builds
Compressed ML models for onboard vehicle inference and large-scale simulation pipelines
Domain
Autonomous transportation / Physical AI / Deep Learning
Deliverable
production ML models
Required skills
Model distillation, Quantization-aware training (QAT), Post-training quantization (PTQ), Knowledge distillation, Pruning and sparsification, Low-rank factorization, Efficient architecture design, Speculative decoding, Distributed training, Python, PyTorch/JAX
Preferred skills
Hardware-aware optimization (TensorRT, ONNX, CUDA), Generative model distillation (diffusion, LLMs, VLMs), Top-tier ML publications, Autonomous vehicles/robotics background
Technologies
PyTorch, JAX, TensorRT, ONNX, CUDA
Responsibilities
Define technical strategy for model distillation across perception, world models, and planning; Design and scale distillation pipelines for generative models and compression techniques; Collaborate with ML Platform, Infrastructure, and Autonomy teams to integrate compressed models; Define benchmarks for efficiency vs. quality trade-offs; Mentor researchers and engineers; Champion best practices and disseminate knowledge; Stay at the cutting edge of model efficiency research.
Seniority
Senior, hands-on IC with technical leadership
