Transformez ce poste en entretien — un CV et une lettre de motivation conçus selon ce que cet employeur recherche.
servescale.ai is seeking a Member of Technical Staff to design, build, and maintain core components of our AI inference platform. You will focus on scalability, reliability, and cost efficiency while collaborating with product, infra, and data teams to optimize model placement and resource utilization across cloud and on‑prem environments.
You will implement backend services and APIs, enhance observability, participate in code reviews, and contribute to technical design and documentation.
servescale.ai is an economics-first, topology-aware AI inference platform that helps enterprises efficiently map models to the right infrastructure. By focusing on cost optimization and performance, the platform enables CIO organizations to deliver AI as a service to internal business and application teams. servescale.ai provides a unified, platform-centric approach that simplifies deployment, scaling, and management of AI workloads across diverse environments. The company is driven by a mission to make enterprise AI more reliable, efficient, and accessible, offering opportunities to work on cutting-edge infrastructure and AI technologies.
As a Member of Technical Staff at servescale.ai, you will design, build, and maintain core components of our AI inference platform, with an emphasis on scalability, reliability, and cost efficiency. You will collaborate with product, infrastructure, and data teams to architect solutions that optimize model placement, resource utilization, and performance across cloud and on-prem environments. Typical responsibilities include implementing backend services and APIs, improving system observability, participating in code reviews, and contributing to technical design discussions and documentation. You will also help troubleshoot production issues, refine deployment pipelines, and support new feature rollouts for enterprise customers. This is a full-time, remote role with cross-functional collaboration across time zones.