# Software Engineer, Tokens and Prompt Structures at Anthropic

- Company: Anthropic
- What the company does: Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems. Backed by Accel, Bessemer and General Catalyst.
- Company website: https://www.anthropic.com/
- Type: Startups (AI role)
- Level: Mid level
- Location: San Francisco, CA | New York City, NY
- Work setup: On-site
- Posted: 2026-09-16
- Apply by: 2026-10-31
- Apply: https://job-boards.greenhouse.io/anthropic/jobs/5421263008
- Page: https://www.1752.vc/careers/jobs/anthropic-software-engineer-tokens-and-prompt-structures/

## About the role

The Encodings Infra team maintains the libraries that engineers and researchers across Anthropic use to encode text and multimodal data into a form that Claude can consume. It also determines Claude’s prompt shape: how a user’s turn is represented to the model, how Claude calls tools and receives tool results, and so on.

## What they're looking for

- Tokenizers or other text/data encoding systems
- Maintaining a widely-used library over a long period of time
- Performance optimization
- Python and/or Rust
- Reinforcement learning or model training infrastructure

Tags: AI Research & Engineering