Position Description

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.

In this role, you will:

• Focus on ensuring that state-of-the-art models run with maximum performance on a wide range of platforms
• Develop concepts for running AI/ML models on various platforms
• Optimize, tune and evaluate AI/ML models for different platforms
• Make the most out of hardware and software platforms in the field of AI/ML
• Ensure that every bit of available performance is used for the best possible user experience

What you will need to succeed:

• Experience in the areas of Machine Learning, Deep Learning, Data Processing and NLP
• Experience in optimizing deep learning models using techniques such as quantization, pruning, knowledge distillation, and model tuning and evaluation
• Experience with optimization of performance-critical algorithms for different CPU (ARM / x86 / Qualcomm) and GPU architectures (NVIDIA) - experience with Qualcomm is a must
• Experience with state-of-the-art performance toolkits, software stacks and profiling tools (Cuda / CuDNN / TensorRT, Jit + Jax)
• Proficient knowledge of Python, C/C++, PyTorch, TensorFlow, Keras
• Fundamental knowledge of ARM/x86 assembly
• Fundamental knowledge about parameter efficient fine-tuning techniques (e.g., LoRA, PEFT)
• Good written and verbal English communication skills