Software Engineer, Tokens and Prompt Structures

Job Overview

As a Software Engineer on the Encodings Infra team at Anthropic, you will own the design and maintenance of libraries that engineers and researchers use to encode text and multimodal data for consumption by Claude, the company's AI model.

Responsibilities:

• Maintain and improve encoding libraries used across Anthropic
• Run experiments to determine optimal ways to feed structured data into Claude
• Design data structures and abstractions to shield the organization from encoding details
• Adapt encoding libraries to support new research directions and production shipping
• Optimize encoding performance across dependent systems

Requirements:

• 5+ years of software engineering experience, particularly with libraries, SDKs, or developer-facing APIs
• Familiarity with ML terminology and LLM architecture
• Experience with complex refactors in large codebases
• Strong communication skills for collaboration with researchers and engineers
• Results-oriented with a bias towards flexibility and impact

Nice to Have:

• Experience with tokenizers or text/data encoding systems
• Maintaining widely-used libraries over time
• Performance optimization knowledge
• Proficiency in Python and/or Rust
• Background in reinforcement learning or model training infrastructure

Compensation:

• Annual salary: $320,000 - $405,000 USD