Job Description
Architect and manage a fully mutable, distributed hybrid infrastructure spanning AWS and RunPod. Your mission: build a cloud- and provider-agnostic stack that can scale to support millions of users engaging with cutting-edge generative AI and real-time video services.
Architect and lead the implementation of a fully mutable, distributed infrastructure across AWS and RunPod. Develop and maintain cloud- and provider-agnostic deployment strategies. Own and evolve automation and infrastructure-as-code (IaC) initiatives using modern open source tooling. Build and optimize CI/CD pipelines to enable rapid and secure deployments.
Establish world-class monitoring, observability, and performance tuning for large-scale distributed systems. Support AI workloads, including GPU-based compute for generative models and real-time video generation. Work closely with ML engineers, data engineers, and product teams to support dynamic and high-throughput workloads. Proactively identify and resolve bottlenecks, continuously improving system reliability and scalability. Lead and mentor a team of DevOps and infrastructure engineers.
About Oh
Oh is building the OpenAI of the spicy content industry and is at the forefront of the generative AI revolution, combining cutting-edge models developed in-house.