Amazon
Are you passionate about cutting-edge technology in Artificial Intelligence and Machine Learning? We are looking for a skilled
Senior Software Engineer
to join our team focused on enhancing the AWS Neuron Inference ecosystem. You will play a crucial role in the development and optimization of advanced LLM Inference components, including Attention, MLP, Quantization, Speculative Decoding, and Mixture of Experts. In this position, you will collaborate closely with chip architects, compiler engineers, and runtime engineers to maximize the performance and accuracy of Neuron devices with a variety of models, such as Llama 3.3 70B, 3.1 405B, DBRX, and Mixtral. Key Responsibilities: Adapt and implement the latest research in LLM optimization to enhance performance on Neuron chips. Collaborate across various teams to ensure seamless integration of new developments. Engage in ongoing mentorship, knowledge-sharing, and code reviews to foster a supportive team environment. Basic Qualifications: 3+ years of professional software development experience. 2+ years of experience in design or architecture of new and existing systems. Proficiency in at least one programming language. Understanding of machine learning models and their architecture, with experience in optimization. Preferred Qualifications: 3+ years navigating the full software development life cycle. Bachelor's degree in Computer Science or equivalent. Hands-on experience with PyTorch or Jax, particularly in developing and deploying LLMs on AI acceleration hardware. Join our inclusive culture, where your contributions will empower us to deliver exceptional results for our customers. We value your career development and will provide opportunities for growth in your engineering expertise. This position is based at our office, and we are currently hiring. Don't miss the chance to be part of a dynamic team innovating in the field of AI.
Senior Software Engineer
to join our team focused on enhancing the AWS Neuron Inference ecosystem. You will play a crucial role in the development and optimization of advanced LLM Inference components, including Attention, MLP, Quantization, Speculative Decoding, and Mixture of Experts. In this position, you will collaborate closely with chip architects, compiler engineers, and runtime engineers to maximize the performance and accuracy of Neuron devices with a variety of models, such as Llama 3.3 70B, 3.1 405B, DBRX, and Mixtral. Key Responsibilities: Adapt and implement the latest research in LLM optimization to enhance performance on Neuron chips. Collaborate across various teams to ensure seamless integration of new developments. Engage in ongoing mentorship, knowledge-sharing, and code reviews to foster a supportive team environment. Basic Qualifications: 3+ years of professional software development experience. 2+ years of experience in design or architecture of new and existing systems. Proficiency in at least one programming language. Understanding of machine learning models and their architecture, with experience in optimization. Preferred Qualifications: 3+ years navigating the full software development life cycle. Bachelor's degree in Computer Science or equivalent. Hands-on experience with PyTorch or Jax, particularly in developing and deploying LLMs on AI acceleration hardware. Join our inclusive culture, where your contributions will empower us to deliver exceptional results for our customers. We value your career development and will provide opportunities for growth in your engineering expertise. This position is based at our office, and we are currently hiring. Don't miss the chance to be part of a dynamic team innovating in the field of AI.