Performance Engineer, Inference Infrastructure & Optimization

Morph is hiring a performance engineer to accelerate inference infrastructure for frontier-scale models. You will work directly with the founders in a small team, delivering measurable improvements in latency and cost while enhancing reliability and throughput. You will optimize kernels, batching, scheduling, routing, and quantization, while building benchmarks and observability to expose bottlenecks. This role offers immediate production impact and access to world-class compute resources. #J-18808-Ljbffr