Senior Systems Engineer, Workers AI
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
TL;DR
Senior Systems Engineer, Workers AI: Designing and building the core infrastructure that powers AI inference across 's global network with an accent on distributed systems and high-performance computing. Focus on sub-second model cold starts, multi-accelerator workload scheduling, and efficient KV cache management.
Location: Austin, TX or London, UK (Hybrid)
Company
is on a mission to help build a better Internet by providing security and acceleration services to millions of websites and Internet properties.
What you will do
- Develop and maintain core components of the serverless inference platform to ensure high availability and scalability for users.
- Optimize the model scheduling system to significantly increase efficiency and resource utilization across our inference infrastructure.
- Implement improvements to the inference request routing logic to enhance overall performance and reduce latency for end-users.
- Drive significant, measurable improvements in the platform's reliability and resilience by identifying and mitigating systemic risks.
- Expand and refine the observability stack, including metrics, logging, and tracing, and fine-tune alerts to proactively identify and resolve production issues.
- Lead complex, cross-functional technical projects from initial concept and design through final deployment and operationalization.
Requirements
- Experience in systems engineering, with a focus on distributed, high-performance systems.
- Expert proficiency in Rust programming, particularly in an asynchronous environment.
- Deep understanding and hands-on experience with relevant networking and application protocols (e.g., TCP, HTTP, WebSocket).
- Experience with scaling and performance optimization techniques, including load balancing and caching in a distributed environment.
Nice to have
- Demonstrable experience with container orchestration platforms, specifically Kubernetes and/or Nomad.
- Familiarity with the challenges and architectures involved in large-scale inference serving (e.g., LLM and diffusion models).
Culture & Benefits
- is committed to protecting the free and open Internet.
- Offers tools to defend against attacks that would otherwise censor journalism and civil society organizations.
- Provides the highest level of protection and reliability for free to state and local governments.
- Released a faster, more secure and privacy-centric public DNS resolver.
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 →