jobs

Software Engineer, Tokens and Prompt Structures

About Anthropic Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers,

Company

Anthropic

Location

San Francisco, CA; New York City, NY

Status

Open

Posted

2026-09-16T14:12:43+00:00

Anthropic's Encodings Infra team maintains the internal libraries that turn text and multimodal data into a form Claude can consume, and defines prompt structure — how a user turn, tool call and tool result reach the model. The engineer designs and maintains those libraries, runs experiments on feeding structured data, carries out refactors, and optimises performance. The posting asks for 5+ years of engineering experience, including maintaining libraries, SDKs or developer-facing APIs, plus enough ML familiarity to work with researchers. Work spans pretraining, finetuning and the API.