Description
Parasail is hiring a Senior/Staff Inference Reliability Engineer to own the end-to-end reliability and production performance of customer inference workloads. The role covers availability, latency, throughput, quality, cost, observability, incident response, capacity analysis, and platform improvements across APIs, routing, scheduling, model servers, GPUs, networking, and cloud infrastructure. Candidates should have at least five years of production, reliability, distributed systems, ML infrastructure, database reliability, or performance engineering experience, along with strong software engineering, observability, and cross-team leadership skills; prior LLM-inference experience is valuable but not required.
