Software Engineer, Tokens and Prompt Structures
$320k - $405k • San Francisco, CA | New York City, NY
Posted 13h ago
Job Location
San Francisco, CA | New York City, NY
Tech Stack
Remote Work Policy
On-site
Categories
LLM Engineer
About the job
Anthropic's mission is to create reliable, interpretable, and steerable AI systems that are safe and beneficial for users and society. The Encodings Infra team maintains the libraries that engineers and researchers use to encode text and multimodal data for Claude, and determines Claude's prompt shape. As a Software Engineer on this team, you will own the design and maintenance of these libraries, ensuring their APIs are intuitive, performance is sharp, and abstractions are solid. Your work will touch systems across the codebase, from pretraining to finetuning to the API, and you will collaborate closely with researchers and engineers to move new encoding ideas from experiment to production.
Responsibilities
- Maintain and improve encoding libraries for engineers and researchers.
- Run experiments to optimize structured data input for Claude.
- Design data structures and abstractions to simplify encoding details for most users while empowering power users.
- Adapt encoding libraries to support new research directions and productionize research ideas.
- Optimize encoding performance across dependent systems.
Requirements
- 5+ years of software engineering experience, with significant time spent maintaining libraries, SDKs, or developer-facing APIs.
- Familiarity with ML terminology and LLM architecture.
- Experience with complex refactors in large codebases.
- Strong communication skills and ability to collaborate with researchers and engineers.
- Results-oriented with a bias towards flexibility and impact.
- Willingness to take on tasks outside of the job description.
- Interest in the societal impacts of AI work.
Benefits
- Annual compensation range: $320,000 - $405,000 USD
- Visa sponsorship available for some roles and candidates.