"inference serving" Jobs
959 open tech roles matching “inference serving”, taken straight from company career pages — not reposted from other job boards. Most in demand right now: Python, Kubernetes, AI/ML. Every listing is re-checked daily and closed roles are removed.
Showing 20 of 959 results
Join Together AI as a Senior Software Engineer to build AI agents for one of the largest GPU fleets, focusing on infrastructure and automation.
Build production AI agent systems for one of the world's largest GPU fleets at Together AI.
Lead the development of models and algorithms for Decagon's real-time voice agents in a collaborative, onsite environment.
Lead applied research and development for AI models at Fiddler AI, ensuring safety and compliance in production applications.
Lead a team to build Anthropic's scheduling platform and improve fleet efficiency in a fast-paced AI environment.
Join Strava as a Lead Data Scientist to drive measurement strategy and enhance AI-driven user experiences.
Join Commure as a Senior Backend Engineer to build a next-generation ambient AI platform for healthcare.
Join SingleStore as a Software Engineer to design and implement core AI/ML platform capabilities in a dynamic, engineering-focused team.
Join Handshake as a Senior Software Engineer to build scalable ML infrastructure for a fast-growing AI data business.
Join Together AI as a Software Engineer Intern to work on impactful projects in a collaborative environment.
Join Together AI to build production AI agents and foundational systems for one of the largest GPU fleets in the world.
Join Baseten as an Account Executive to drive sales and build relationships in a fast-paced AI startup environment.
Join Algolia as a Site Reliability Engineer to build and operate production infrastructure supporting AI-related workloads and services.
Join Kodiak Robotics as a Senior Helpdesk to lead IT support and enhance employee technology experience in a growing autonomous transportation company.
Join Etched as a Global Supply Manager to lead sourcing strategies for mechanical components in a fast-paced hardware startup.