Research Scientist (AI Model Optimization), IPV, ARTC
Core
Lead research into state-of-the-art AI model optimization techniques (Quantization-Aware Training, Pruning, Knowledge Distillation, NAS) to minimize latency for high-throughput camera and sensor data streams in manufacturing environments.
Role type
Senior IC research scientist (AI model optimization)
Builds
Scalable AI deployment architectures and optimized models for factory-level software stacks
Domain
Manufacturing / Edge AI / Hardware-Software Co-design
Deliverable
production ML models
Required skills
Model compression (Pruning, Quantization, Distillation), AI Inference Engines (TensorRT, ONNX Runtime, OpenVINO), C++, Python, Parallel Computing (CUDA, OpenCL), Mixed-Precision Training, Neural Architecture Search, Hardware-software co-design
Preferred skills
Experience with NVIDIA Jetson, TensorRT, FPGAs, specialized AI accelerators
Technologies
TensorRT, ONNX Runtime, OpenVINO, CUDA, OpenCL, NVIDIA Jetson, FPGAs
Responsibilities
Lead research into optimization techniques to minimize latency; Design and implement scalable AI deployment architectures; Conduct hardware-software co-design for specific deployment targets; Develop asynchronous data pipelines; Establish performance profiling benchmarks; Integrate optimized models into factory-level software stacks
Seniority
Senior, hands-on IC
