The Encodings Infra team maintains libraries that encode text and multimodal data for Claude, designing APIs, running experiments, and optimizing performance across pretraining, finetuning, and API layers. The role collaborates closely with researchers and engineers to ship encoding innovations to production.
Software Engineer, Tokens and Prompt Structures na Anthropic
Híbrido - San Francisco, CA, USA
Ver mais vagas na AnthropicSalary
USD 320,000 - 405,000
Requirements
Skills
- 5+ years of software engineering experience, with meaningful time spent maintaining libraries, SDKs, or developer-facing APIs
- Familiarity with ML terminology and LLM architecture
- Experience carrying out complex refactors in large codebases
- Strong communication skills and enjoy working closely with researchers and engineers to understand what they need
- Results-oriented, with a bias towards flexibility and impact
- Pick up slack, even if it goes outside your job description
- Care about the societal impacts of your work
Responsibilities
- Maintain and improve the encoding libraries used by engineers and researchers across Anthropic
- Run experiments to determine the optimal way to feed structured data into Claude without confusing it
- Design data structures and abstractions that shield most of the organization from the details of how encoded data works while enabling power users
- Adapt the encoding libraries to support new research directions as they emerge, and make sure that we can ship these research ideas to production
- Optimize encoding performance across the systems that depend on these libraries
Technologies
PythonRustTokenizersML terminology and LLM architecturePerformance optimizationReinforcement learningModel training infrastructure
Descubra se seu currículo está pronto para esta vaga
Veja como nossa IA pode otimizar seu currículo e aumentar suas chances de conseguir esta posição.