Jobs at Runware

Build and maintain internal and public-facing APIs and services powering the Web App and developer experience. Develop API functionality, Admin API systems, WebSocket and REST behavior, and usage and billing integrations with Stripe. Investigate production issues and security vulnerabilities, write and review tested code, make technical decisions, and collaborate across engineering, Product, and Design teams.

Lead the development of Runware's serverless platform by building core systems for AI workload management and providing technical guidance to the team.

Lead development of Runware’s AI platform, including scalable backend APIs, SDKs, developer tools, and inference orchestration systems. Design high-performance distributed architectures, optimize image and video model integrations, improve reliability and observability, shape technical direction, and mentor engineers. Collaborate across platform, infrastructure, and product teams to deliver robust developer experiences and maintainable systems.

Experiment with generative image and video models, build advanced ComfyUI workflows and automated pipelines, and create high-quality demos, examples, guides, and social content. Translate technical experimentation into engaging developer- and creator-facing material, rapidly evaluate new model releases, and collaborate with Growth, Product, and Engineering on launches and use cases.

Lead end-to-end ML initiatives: integrate and fine-tune models, optimize GPU inference for latency and throughput, build evaluation and monitoring tooling, collaborate on scalable serving systems, and mentor engineers.

The Staff DevOps Engineer will enhance and manage infrastructure for AI inference, focusing on speed, resilience, and automation across GPU fleets and production systems.

Ensure reliability, performance, and resilience of Runware's distributed, GPU-backed production platform. Define SLIs/SLOs and observability, investigate incidents across services, databases, networking and queues, automate remediation and deployment safety, participate in on-call rotations, conduct RCA and implement long-term fixes, and collaborate on capacity planning and scaling.