ai engineer for AI hardware

The team builds computers designed specifically for AI, combining computer architecture, ASIC design, advanced systems, neural network compilers, neural networks, LLMs, and CNNs to develop next-generation computing.

• Design, implement, and iterate on neural network architectures using PyTorch for optimal performance across diverse tasks;
• Train, validate, and fine-tune machine learning models using relevant datasets to ensure high accuracy and robustness;
• Investigate and troubleshoot model performance issues, iterating on models and techniques to improve results;
• Analyze how models map onto Tenstorrent devices through compilation steps and kernels;
• Identify functionality and performance gaps and propose innovative solutions;
• Collaborate with cross-functional teams working on compilers, neural networks, LLMs, and CNNs;
• Deploy neural networks for various applications, ensuring scalability and reliability.

• 5+ Years of experience in machine learning and AI engineering;
• At least 1 year of relevant leadership experience;
• Proficiency in Python and hands-on experience with PyTorch for developing and training deep learning models;
• Expertise in designing, training, and deploying neural networks for various applications;
• Understanding of machine learning fundamentals, including supervised and unsupervised learning techniques;
• Experience investigating and troubleshooting model performance issues;
• Ability to map models onto specialized AI hardware through compilation steps and kernels;
• Strong English communication skills at B2 level or higher;
• Nice to have: Experience with C++ and kernel programming, knowledge of GPU/AI-accelerator architectures.

• No conditions specified