jobs

Staff AI Product Engineer

About Nscale Nscale is taking on the hyperscalers by building a vertically integrated GenAI cloud platform. We own the data centers, software, and applications that power today's AI stack using sustainable technology solutions. We thrive on

Company

Nscale

Location

Houston; New York; San Francisco; Seattle

Status

Open

Posted

2026-09-15T18:26:49+00:00

Nscale is hiring a staff-level engineer to own the architecture of its inference serving and reinforcement learning systems, plus the APIs other engineers use. The work covers routing, batching, KV cache management, quantization, RLHF and preference-optimization pipelines, and developer-facing SDKs. The role spans two to four teams and includes coaching junior engineers and setting cross-team standards. Requirements include 8–12 years of experience, deep production LLM inference and RL expertise, Python and PyTorch, and large-scale GPU work. Open-source contributions are preferred.