AI Infrastructure Architect

Lead the software architecture and technical roadmap for an advanced AI platform.
Write system specifications and technical documentation for software products.
Research AI infrastructure, SaaS platforms, model serving, and inference technologies and trends.
Work closely with engineering teams to translate technical capabilities into product value and customer needs.
Drive performance, scalability, and feature optimization across software platforms.
Define performance goals and lead profiling, benchmarking, and optimization efforts for GenAI and distributed AI workloads.
Collaborate with customers, partners, and open-source communities to ensure ecosystem compatibility and adoption.
Provide technical leadership and mentor software engineers.
דרישות התפקיד
7+ years of software engineering experience, including 3+ years in software architecture or technical leadership.
Strong experience with Kubernetes, cloud-native architectures, and distributed systems.
Deep knowledge of GenAI/LLM infrastructure, model serving, and AI inference platforms.
Experience building SaaS or management platforms for production environments.
Hands-on experience with CI/CD, observability, performance optimization, security, and automation.

Nice to Have

Experience with GPU-based AI inference infrastructure and distributed AI workloads.
Familiarity with LLM serving frameworks (vLLM, Triton, TensorRT-LLM, KServe, Kubeflow).
Knowledge of GPU communication technologies (NCCL, NVLink, GPUDirect RDMA).
Experience with Kubernetes ecosystem tools (Prometheus, Grafana, Helm, Argo CD, Istio).
Experience deploying software in on-prem, edge, private cloud, or hybrid environments.