ML Systems Engineer: Scale Training & Inference

Engram is seeking an ML Systems Engineer to design, optimize, and scale training and inference workloads across GPUs and distributed systems. You’ll collaborate with researchers and performance engineers to bridge cutting‑edge AI research with production systems.

The role requires a Bachelor’s degree and 5+ years of experience in ML or training/inference, contributing to personalization features, memory retrieval, and low‑latency serving in a fast‑paced startup environment based in San Francisco.