Build and own a multi-tenant platform connecting enterprise customers and sovereign deployments to inference infrastructure. Responsibilities include authentication, tenant isolation, quotas, rate limiting, usage metering, entitlements, public inference APIs, SSO, access controls, audit logs, data residency, and security testing. The role requires strong Python and backend or platform engineering expertise, API design experience, and familiarity with billing, credits, reconciliation, regulated environments, and enterprise identity systems.

Own and optimize the cost, throughput, latency, and reliability of an AI inference stack. Responsibilities include improving KV-cache management, batching, speculative decoding, quantization, routing, and long-context workloads; tuning serving engines; and building profiling systems. The role requires production experience with inference infrastructure, GPU performance, model serving, and systems programming.

The Research Scientist/Engineer will innovate algorithms for real-time adaptation, optimize ML systems, and ensure impactful product interactions.