Software Engineer, Tokens and Prompt Structures

Anthropic
San Francisco, New York
Workplace: OnsiteFull timeUSD 320,000 - 405,000 annuallyFunction: Software EngineeringExperience: 5+ yearsEducation: bachelorsSkills: ["Communication","Collaboration","Results-oriented","Flexibility","Bias toward impact"]

Own the design and maintenance of Anthropic’s encoding libraries that turn text and multimodal data into Claude-consumable inputs, including prompt structure and tool calling. Partner with researchers and engineers across the codebase to run experiments, design abstractions, refactor large systems, and optimize library performance. Enable downstream teams to ship new encoding ideas reliably from research to production without needing to understand encodings internals.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Anthropic
Anthropic
1 day ago

Software Engineer, Tokens and Prompt Structures

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 20 hours agoStatus: Live

Job Summary

Own the design and maintenance of Anthropic’s encoding libraries that turn text and multimodal data into Claude-consumable inputs, including prompt structure and tool calling. Partner with researchers and engineers across the codebase to run experiments, design abstractions, refactor large systems, and optimize library performance. Enable downstream teams to ship new encoding ideas reliably from research to production without needing to understand encodings internals.
Location: San Francisco, New York
Workplace: Onsite
Employment Type: Full time
Job Function: Software Engineering
Seniority: Mid level

Key Responsibilities

  • •Maintain and improve encoding libraries used by engineers and researchers across Anthropic.
  • •Run experiments to determine the optimal way to feed structured data into Claude.
  • •Design data structures and abstractions that shield most of the organization from encoding details while enabling power users.
  • •Adapt encoding libraries to support new research directions and ship them to production.
  • •Optimize encoding performance across systems that depend on the libraries.

Pay and Benefits

Salary: USD 320,000 - 405,000 annually

Key Requirements

  • •5+ years of software engineering experience maintaining libraries, SDKs, or developer-facing APIs.
  • •Familiarity with ML terminology and LLM architecture sufficient to work with researchers and interpret experiment results.
  • •Experience carrying out complex refactors in large codebases.
  • •Strong communication skills and ability to work closely with researchers and engineers.
  • •Results-oriented mindset with flexibility and bias toward impact.
Experience:5+ yearsMLLLMsResearch to production
Education:Bachelor's
Skills:CommunicationCollaborationResults-orientedFlexibilityBias toward impact
Languages:English
Tech Stack:PythonRust

Company Brief

Anthropic
Develops large-scale AI systems and safety research to create reliable, steerable, and interpretable AI assistants and models for commercial and research applications.
Industry: AI & Machine Learning
Company Size: Enterprise (1,001+ employees)
Growth: Scaleup
Valuation: Unicorn (USD 1B+)
Funding: Series C
Headquarters: San Francisco, United States
Founded: 2021
WebsiteLinkedIn