Applied AI Engineer, Inference

📋 Description Build benchmarking workflows to measure latency, throughput, quality regressions, and cost. Benchmark inference stack against realistic workloads and baselines to identify gaps. Profile model-serving across frameworks, runtimes, and hardware to find bottlenecks. Drive optimizations for customer workloads, tuning serving configs and validating changes. Design and run experiments on model-serving techniques like quantization and caching. Partner with inference engineers to…

Posted Jul 30, 2026 · via tryremotely · listing belongs to the original publisher