Software Engineer (Tokens and Prompt Structures)

Join Anthropic, a leading AI safety and research company, as a Software Engineer on the Encodings Infra team. In this role, you will design and maintain libraries used for encoding text and multimodal data, ensuring their performance and usability. You will collaborate closely with researchers and engineers, and your work will have a direct impact on the capabilities of our AI model, Claude.

• Maintaining and improving the encoding libraries used by engineers and researchers across Anthropic.
• Running experiments to determine the optimal way to feed structured data into Claude without confusing it.
• Designing data structures and abstractions that shield most of the organization from the details of how encoded data works while enabling “power users”.

• Are results-oriented, with a bias towards flexibility and impact
• Pick up slack, even if it goes outside your job description
• Have experience carrying out complex refactors in large codebases
• Care about the societal impacts of your work
• Have strong communication skills and enjoy working closely with researchers and engineers to understand what they need
• Have 5+ years of software engineering experience, with meaningful time spent maintaining libraries, SDKs, or developer-facing APIs
• Have familiarity with ML terminology and LLM architecture — you don't need to be an ML expert, but enough understanding to work effectively alongside researchers and understand the results of experiments
• We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed. Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you're interested in this work
• Reinforcement learning or model training infrastructure
• Performance optimization
• Python and/or Rust
• Tokenizers or other text/data encoding systems
• Maintaining a widely-used library over a long period of time