Pearl Research is an AI lab building custom algorithms and systems that make frontier LLM inference dramatically faster and cheaper. To power both our live serverless platform and our internal research, we run a growing multi-cloud fleet of heterogeneous hardware.
We’re hiring an AI Infrastructure Engineer to own the architecture and operation of our production and internal clusters, driving core design around automated deployments, fast cold starts, and smart compute scheduling across live serving, research, and dev workloads. We’re looking for strong engineering skills and an eagerness to learn, not prior AI/GPU experience or familiarity with a specific toolset.
You’ll join a small, stacked Tel Aviv team of IOI/IMO medalists, CS professors, and engineers from NVIDIA, Google, and Amazon, backed by Lightspeed, Ribbit, and leaders from OpenAI and DeepMind. Capacity and traffic are scaling fast, giving you greenfield ownership to shape our infrastructure from the ground up without legacy baggage or red tape.
Send your CV to careers@pearlresearch.ai
