Senior Machine Learning Engineer - AI Foundation
Core
Building state-of-the-art ML infrastructure to train and accelerate inference for very large foundation models enabling next-generation end-to-end autonomous driving solutions.
Role type
Senior Machine Learning Engineer (AI Foundation / Model Optimization)
Builds
Optimized transformer-based LLMs and model graphs for low-latency, high-throughput inference across GPUs, CPUs, and edge accelerators.
Domain
Autonomous driving / AI Foundation Models
Deliverable
production ML models
Required skills
PyTorch, Transformer architecture, CUDA, Triton, Model Quantization, Knowledge Distillation, Model Pruning, KV-cache optimization, Python, C++
Preferred skills
Autonomous driving industry experience, Torchscript, Nvidia TensorRT, GPU/CPU/NPU/DSP architecture knowledge, Memory bandwidth and compute bottleneck analysis
Technologies
PyTorch, CUDA, Triton, Torchscript, Nvidia TensorRT
Responsibilities
Optimize transformer-based LLMs for low-latency and high-throughput inference; Optimize kernels and model graphs using CUDA, Triton, and custom fused operators; Implement and benchmark quantization, knowledge distillation, pruning, and KV-cache optimization; Deploy optimized models across GPUs, CPUs, and edge accelerators; Contribute to internal tooling and documentation for model optimization flows.
Seniority
Senior, hands-on IC