Perception Deployment Engineer - Model Deployment & Optimization

$199,000 – $270,000 · Posted 2 days ago

BostonLast seen 1 day ago

Summary

The Perception Deployment Engineer will optimize and deploy large-scale multi-modal foundation models, LLMs, and vision models to power- and thermal-constrained vehicle edge devices. Responsibilities include writing production C++ and CUDA code for real-time inference, implementing model compression (quantization, pruning, mixed-precision), architecting TensorRT compilation pipelines, and developing custom ML operators and CUDA kernels to achieve low-latency, deterministic execution. The role demands deep expertise in model optimization techniques, edge AI accelerators, and rigorous parity validation between PyTorch frameworks and compiled binaries.

Data Science C++Machine Learning Python 3d Object Detection 3d Occupancy Networks Autonomous Driving Perception Bev Bf16 Cuda Custom ML Operators Edge Deployment Flashattention Foundation Models Fp16 Fp8 Int8 Kv Cache Optimization Lidar Linear Attention LLM Large Language Models Mixed Precision Inference Model Compression Multi Modal Sensor Fusion Onnx Pagedattention Pruning Ptq PyTorch Qat Quantization Radar Tensorrt Tensorrt LLM Tensorrt Plugins Torch Compile Vision Vla Vlm