Key skills
TypeScriptJavaScriptReactJSXASTsCode transformationCompilation conceptsLLM integrationsAI modelsPerformance debuggingPlatform engineeringAPIsSLAsPrompt engineeringRAG patternsModel evaluationCode generation modelsAST-level code manipulationAgentic workflowsMulti-step LLM pipelinesDesign systemsComponent librariesRendering pipelineLayout pipelineGraphics pipelineAILLMRAGAgenticFigma
About this role
Figma is a company dedicated to making design accessible to all, and they are seeking a Software Engineer for their Code Platform team. This role focuses on building AI-driven systems that enhance the integration between design and code, ensuring seamless workflows and improving the overall product experience.
Responsibilities:
- Design, build, and improve code ↔ design translation pipelines, including AI-powered and agentic workflows
- Build and iterate on LLM integrations that power code generation, design interpretation, and agentic feature surfaces
- Design evaluation frameworks for AI-generated code outputs quality, correctness, and format fidelity
- Diagnose and resolve performance bottlenecks and long-running tasks that impact product SLAs
- Improve correctness, reconciliation, and fidelity across complex design system and layout edge cases
- Build scalable serialization pipelines, internal APIs, and platform utilities
- Partner with product leads to define long term product enablement and build foundational infra
- Improve observability and ownership of key metrics (latency, success rate, correctness)
- Support and drive architectural direction and long-term platform strategy for a translation surface
- Mentor engineers and shape the long-term team structure
Requirements:
- 5+ years of software engineering experience, especially in web, platform, or infrastructure engineering
- Strong TypeScript/JavaScript and modern frontend fundamentals
- Deep experience with declarative UI systems (React, JSX, or similar)
- Familiarity with ASTs, code transformation, or compilation concepts
- Experience building features that integrate LLMs or AI models into a product not just using AI tools, but shipping with them
- Experience debugging performance, rendering, or pipeline latency issues
- Experience building complex, cross-team platforms with multiple stakeholder groups
- Experience with prompt engineering, RAG patterns, or model evaluation
- Experience with code generation models or AST-level code manipulation
- Prior work on agentic workflows or multi-step LLM pipelines
- Experience with MCP, tool-use APIs, or AI developer ecosystems
- Experience building design systems or component libraries
- Platform or infrastructure engineering experience (APIs, observability, SLAs)
- Rendering, layout, or graphics pipeline knowledge