AI Platform Team Lead – AI Security

About the role

Cato Networks is building a real‑time AI runtime platform that powers security algorithms across its global cloud and PoPs. We are looking for a hands‑on AI Platform Team Lead to design, build, and lead the team that delivers a high‑throughput, low‑latency engine for GPU‑based models and CPU‑based security logic.

Key responsibilities

• Recruit, mentor, and provide technical direction for the AI Platform team.
• Own the AI security runtime platform, ensuring performance, reliability, autoscaling, and operational health.
• Design the orchestration layer that runs GPU models, CPU heuristics, and security logic as a single production engine.
• Manage the model lifecycle platform, including registry, versioning, deployment, monitoring, and safe rollout.
• Collaborate with research and algorithm teams to productionize AI security models at scale.

Required profile

• 3+ years of leadership experience as a team lead, tech lead, or engineering manager.
• 3+ years of hands‑on experience in AI inference, production ML infrastructure, or model serving.
• Strong system design skills for distributed, high‑performance, and reliable infrastructure.

Required skills

• Production inference technologies: Triton, vLLM, CUDA, Kubernetes, Docker, PyTorch, ONNX, TensorRT.
• Backend programming: Go (or C++, Rust, Java).
• Performance optimization, scalability, observability, and SLO‑driven production ownership.