Senior ML Engineer, Zendar

• 3+ years of experience in optimizing deep neural networks and deploying them across diverse compute platforms, including but not limited to Qualcomm, and NXP
• Proficiency in modern Python and C++
• Expertise in designing and optimizing neural network models for edge deployment
• Familiarity with model quantization, quantized aware training, NAS and model pruning, and other techniques for efficient deployment on edge devices
• Experience in training, testing, and verifying optimized neural network models
• Proficient in at least one major deep learning framework (e.g., PyTorch, TensorFlow)
• Strong communication skills and proven ability to collaborate effectively across functions

Desirable

• At Zendar, we’ve developed a robust semantic spectrum perception pipeline using millions of training samples, achieving high-performance object detection that positions radar as a key sensor for safety and autonomy in mass-market vehicles. Our models are designed for deployment across diverse edge devices aimed at series production
• In this role, you will be a core member of the machine learning and perception team, focusing on optimizing and deploying our machine learning models on targeted edge compute platforms. Key responsibilities include:
• Deeply understanding the capabilities, TOPS, and memory bandwidth of each target platform
• Designing or adapting models to align with the hardware specifications and supported operations of the edge device
• Training and testing models to ensure they meet all runtime and performance requirements
• You will work closely with the perception team to shape our perception module for future production series, while also collaborating with chip designers to influence the development of compute architectures that align with our pipeline’s requirements
• As the key expert on edge deployment, you will also work closely with our product team and external partners to bring our solution to market