C
AI Platform Engineering Lead
PresencialTiempo completoAI EngineeringCybersecurityEnterprise Software
Lead the team responsible for a high-throughput, low-latency AI runtime platform that executes GPU models, CPU heuristics, and security logic in production cloud environments. Own platform architecture, engineering execution, model serving, reliability, and the lifecycle from AI research to large--
Responsabilidades
- Build and lead the AI Platform team, including hiring, mentoring, architecture, technical direction, and delivery.
- Own the AI security runtime platform for high-throughput, low-latency inline security decisions across global cloud and physical points of presence.
- Design orchestration for GPU models, CPU heuristics, and security logic within one production engine.
- Own observability, service-level objectives, autoscaling, reliability, rollout, rollback, and operational health.
- Own the model lifecycle platform, including registry, versioning, deployment, monitoring, and safe production rollout.
- Collaborate with research and algorithm teams to productionize AI security models and algorithms at scale.
- Define the long-term strategy for AI runtime and model serving.
Requisitos
- At least 3 years of leadership experience as a team lead, technical lead, or engineering manager.
- At least 3 years of hands-on experience with AI inference, production machine-learning infrastructure, model serving, or AI runtime platforms.
- Experience with production inference technologies such as Triton, vLLM, CUDA, Kubernetes, Docker, PyTorch, ONNX, TensorRT, or comparable tools.
- At least 3 years of experience with Go, or strong experience with a comparable high-performance backend language such as C++, Rust, or Java.
- Experience with performance optimization, scalability, observability, and SLO-driven production ownership.
- Strong system design skills involving distributed systems, performance, reliability, and production infrastructure.
Se valora
- Experience with GPU optimization, scheduling, resource efficiency, quantization, runtime acceleration, or large-scale model serving.