(Senior) AI/ML Engineer - Performance Optimization (f/m/d)

<h2 id="position-description">Position Description</h2> <p>As a (Senior) AI/ML Engineer - Performance Optimization (f/m/d) at Cinemo, you will play a critical role in the development and enhancement of our AI/ML powered applications for a wide range of automotive hardware (x86/x64, ARM/ARM64, Qualcomm) and OS platforms such as Android Automotive OS (AAOS) and Linux. Your primary responsibility will be to port and optimize AI/ML models for various hardware and OS customer platforms.</p> <h2 id="in-this-role-you-will">In this role, you will:</h2> <ul> <li>Focus on ensuring that state-of-the-art models run with maximum performance on a wide range of platforms</li> <li>Develop concepts for running AI/ML models on various platforms</li> <li>Optimize, tune and evaluate AI/ML models for different platforms</li> <li>Make the most out of hardware and software platforms in the field of AI/ML</li> <li>Ensure that every bit of available performance is used for the best possible user experience</li> </ul> <h2 id="what-you-will-need-to-succeed">What you will need to succeed:</h2> <ul> <li>Experience in the areas of Machine Learning, Deep Learning, Data Processing and NLP</li> <li>Experience in optimizing deep learning models using techniques such as quantization, pruning, knowledge distillation, and model tuning and evaluation</li> <li>Experience with optimization of performance-critical algorithms for different CPU (ARM / x86 / Qualcomm) and GPU architectures (NVIDIA) - experience with Qualcomm is a must</li> <li>Experience with state-of-the-art performance toolkits, software stacks and profiling tools (Cuda / CuDNN / TensorRT, Jit + Jax)</li> <li>Proficient knowledge of Python, C/C++, PyTorch, TensorFlow, Keras</li> <li>Fundamental knowledge of ARM/x86 assembly</li> <li>Fundamental knowledge about parameter efficient fine-tuning techniques (e.g., LoRA, PEFT)</li> <li>Good written and verbal English communication skills</li> </ul>