Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Staff Software Engineer (AI): Building and maintaining high-performance inference infrastructure for Claude models with an accent on compute efficiency, distributed orchestration, and request routing at scale. Focus on addressing critical infrastructure blockers across diverse AI accelerators, optimizing performance, and enabling breakthrough research in next-generation model development.
Location: Dublin, Ireland; hybrid policy requires staff to work from an office at least 25% of the time
Annual salary: €295,000–€355,000 EUR
Company
Anthropic develops reliable, interpretable, and steerable AI systems intended to be safe and beneficial for users and society.
What you will do
- Build and maintain critical inference systems serving Claude to millions of users.
- Design intelligent routing algorithms and optimize request distribution across thousands of AI accelerators.
- Develop autoscaling and large-scale orchestration for production, research, and experimental workloads.
- Build deployment pipelines for releasing new models and support new model architectures.
- Integrate AI accelerator platforms across multiple cloud environments and tune performance using production observability data.
- Contribute to inference features such as structured sampling, prompt caching, and geographic routing.
Requirements
- Significant software engineering experience, particularly with distributed systems.
- Experience with performance optimization, large-scale service orchestration, or intelligent request routing.
- Experience implementing and deploying machine learning systems at scale.
- Bachelor’s degree or an equivalent combination of education, training, and experience in a relevant field.
- Strong communication skills and the ability to collaborate in a technically rigorous research environment.
- Visa sponsorship is available, subject to role and candidate eligibility.
Nice to have
- Experience with LLM inference optimization, batching, and caching strategies.
- Experience with Kubernetes and cloud infrastructure, including AWS or GCP.
- Proficiency in Python or Rust.
Culture & Benefits
- Collaborative work across research, engineering, policy, and business teams.
- Flexible working hours and an office environment for collaboration.
- Competitive compensation, optional equity donation matching, generous vacation, and parental leave.
- Work focused on trustworthy AI research and its societal implications.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →