Claude Code Tooling & Evaluation Engineer
Core
Develop tools, workflows, and evaluation systems to improve AI-assisted software development and code quality.
Role type
AI tooling and evaluation engineer
Builds
Tooling around Claude Code and AI coding assistants, automated evaluation pipelines, internal AI engineering utilities
Domain
Software engineering, AI/LLM applications, developer productivity
Deliverable
production ML models
Required skills
Python, Git, developer tooling, LLM-powered coding assistants, automated testing, debugging, code review
Preferred skills
Claude Code, MCP (Model Context Protocol), LangChain, OpenAI SDK, CI/CD, code quality tools
Responsibilities
Build tooling around Claude Code and AI coding assistants, Evaluate AI-generated code quality, Develop automated evaluation pipelines, Improve developer workflows, Create internal AI engineering utilities, Benchmark AI coding performance
Seniority
Mid-level, hands-on IC