Postman

The Member of Technical Staff, AI Platform & Architecture (Infrastructure) role at Postman focuses on building and maintaining the foundational systems and distributed infrastructure for AI model post-training, inference, and data pipelines. This involves optimizing performance for accelerators, building observability tools, and partnering with teams on AI infrastructure requirements and roadmap. The role requires experience with GenAI infrastructure, distributed systems, cloud computing, and scaling AI workloads.

This role focuses on ensuring the reliability, scalability, and performance of Postman's AI-powered API and agentic systems in production. It involves developing and managing reliability metrics (SLOs), implementing observability and monitoring, designing automated failover and recovery strategies, optimizing resource utilization (especially GPU/accelerator efficiency), and leading efforts to build internal tooling for AI system stability. The role requires experience in AI reliability engineering, SRE, or DevOps for distributed systems, with a strong understanding of AI system challenges and integration of AI-specific metrics into reliability frameworks.