Senior Software Development Engineer for AI/ML Model Inference

Join our dynamic team as a Senior Software Development Engineer focused on AI/ML Model Inference! This role is pivotal in developing and optimizing the AWS Neuron software stack, specifically for the AWS Inferentia and Trainium cloud-scale machine learning accelerators. Your contributions will include: Developing, enabling, and tuning performance for a diverse range of large language models (LLMs) including Llama, DeepSeek, stable diffusion, and vision transformers. Collaborating closely with compiler and runtime engineers to create distributed inference solutions using Trainium and Inferentia. Enhancing inference performance for both latency and throughput utilizing Python, PyTorch, or JAX. Contributing to the support of distributed inference in the Neuron SDK. As part of your daily responsibilities, you will: Design and implement high-impact solutions for a broad customer base. Participate in design discussions and conduct code reviews to ensure high-quality software. Engage with both internal and external stakeholders to drive business decisions. Work in an innovative, startup-like environment where your impact is felt immediately. Our team values knowledge-sharing and mentorship, ensuring new members receive comprehensive support. We care about your career growth, and our emphasis on personal development will empower you to take on complex tasks in the future. Basic Qualifications: 5+ years of professional software development experience. 5+ years of experience in system design or architecture with a focus on reliability and scaling. Strong understanding of machine learning principles, particularly LLM architectures, and inference optimization techniques. Proficient in at least one programming language. Preferred Qualifications: 5+ years of experience covering the full software development life cycle. Master’s degree in computer science or a related field. This role emphasizes adhering to both company standards and local laws, fostering a cooperative work environment focused on exceptional customer service. We encourage qualified applicants to apply, including those with backgrounds that may have been overlooked due to the Fair Chance Ordinance.