# Software Engineer, Tokens and Prompt Structures at Anthropic

> Open role observed by RunReq as of 2026-10-15T00:28:46.553805+00:00.

## Role details

- Company: [Anthropic](http://runreq.com/company/anthropic/index.md)
- Location: San Francisco, CA \| New York City, NY
- Team: AI Research & Engineering
- Compensation: $320K–$405K /YR
- First observed: 2026-09-17T01:46:06.618816+00:00
- Days open: 28
- Employer posting: [View the authoritative posting](https://job-boards.greenhouse.io/anthropic/jobs/5421263008)

## Shortened description

### Key responsibilities

- Maintain and improve encoding libraries used by engineers and researchers.
- Design data structures and abstractions for encoded data and prompt structures.
- Run experiments and adapt encoding libraries to support research and production.
- Optimize encoding performance across systems that depend on these libraries.

### Qualifications needed

- Have a bachelor's degree or equivalent education, training, or experience in a relevant field, plus at least five years of software engineering experience.
- Understand ML terminology and LLM architecture well enough to work with researchers and interpret experiment results.
- Have experience completing complex refactors in large codebases.
- Preferred: Experience with tokenizers, widely used libraries, performance optimization, Python, Rust, reinforcement learning, or model training infrastructure.

## Hiring context

- Open roles on this team: 66
- Newly observed on this team in 30 days: 7
- Company median days open: 55

## Interpretation

- RunReq records observed job postings; it does not show applicant volume or completed hires.
- The linked employer posting is authoritative for the full description and application process.
- Human-readable job page: http://runreq.com/jobs/c214a481-1d23-845a-a0be-25b46633836b
- Site-wide agent directory: http://runreq.com/llms.txt