Amazon
Join the team at AWS Neuron, where we are building the complete software stack for AWS Inferentia and Trainium cloud-scale machine learning accelerators. We are looking for a passionate Senior Software Engineer to contribute to our Machine Learning Inference Applications team. In this role, you will focus on the development and performance optimization of essential components for LLM Inference, including Attention, MLP, Quantization, Speculative Decoding, and Mixture of Experts.
Your responsibilities will include:
Adapting cutting-edge research in LLM optimization for Neuron chips, maximizing performance for both open-source and internally developed models.
Collaborating with chip architects, compiler engineers, and runtime engineers to ensure the best outcomes for Neuron devices across various models such as Llama 3.3 70B, 3.1 405B, DBRX, and Mixtral.
Our team prides itself on fostering a welcoming environment for new members, featuring a diverse mix of experience levels. We prioritize mentorship and knowledge-sharing, ensuring that all team members receive one-on-one guidance and constructive code reviews. We are committed to your professional growth and will assign projects that challenge and develop your engineering expertise.
Basic Qualifications:
3+ years of professional software development experience (non-internship).
2+ years of design or architecture experience with systems (design patterns, reliability, scaling).
Proficiency in at least one programming language.
Understanding of machine learning models, their architecture, training, and inference lifecycles, with practical experience in model performance optimization.
Preferred Qualifications:
3+ years of full software development life cycle experience, covering coding standards, code reviews, build processes, testing, and operations.
Bachelor's degree in computer science or a related field.
Hands-on experience with PyTorch or Jax, particularly in developing and deploying LLMs in production environments using GPUs, Neuron, TPU, or other AI acceleration hardware.
We are an equal opportunity employer and value a diverse workforce. We are committed to providing a supportive environment for all employees, including those with disabilities. If you require accommodations during the application process, please let us know.
The base pay for this position varies based on geographic location, ranging from $129,300/year to $223,600/year. In addition to a competitive salary, we offer a comprehensive total compensation package that includes various benefits.
This position will remain open until filled. Interested candidates should apply through our career site.