> Markdown version of [/jobs/ext/4716639-information-designer-ii-26-03441](https://www.wearedevelopers.com/jobs/ext/4716639-information-designer-ii-26-03441). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Information Designer II: 26-03441

- **Company:** Akraya, Inc.
- **Location:** Mountain View, CA, United States
- **Salary:** $93,600 - $104,000
- **Contract:** Permanent contract
- **Skills:** AI Evaluation, HTML, Artificial Intelligence, Data Analysis, Data Files, Python (Programming Language), Performance Tuning, Regular Expressions, Tensorflow, Extensible Markup Language (XML), Chatbots, Retrieval-Augmented Generation, Large Language Models, Claude Code, Prompt Engineering, Agentic-AI, Natural Language Understanding, Programming Languages
- **Published:** November 14, 2026
- **Apply:** https://www.careerbuilder.com/job-details/information-designer-ii-26-03441-mountain-view-ca--2aa496bb-3e19-4ea9-9c9f-7e88507af7cc

## About the Role

Artificial Intelligence (AI), Data Analysis, Data Sets, Conversation Engine, Quality Management, Performance Management, Analysis Skills, Customer Experience, Data Science, Process Improvement, 8+ years of design experience, including 4+ years in Conversation Design.
1+ year of experience with AI agentic platforms.
Strong expertise in prompt engineering, AI tools, and data analysis.
Understanding of LLMs, NLP/NLU, RAG, or machine learning frameworks.
Working knowledge of Python, HTML, XML, Regex, or similar coding languages., Experience in conversational AI, chatbots, voice assistants, AI evaluation, or generative AI products is preferred.

## Description

This role focuses on improving the quality and accuracy of AI-powered chatbots and voice assistants. You will design conversational experiences, build golden datasets, evaluate AI-generated responses at scale, and provide insights to improve AI performance., Build AI skills using Claude Code or similar tools to generate golden datasets.
Evaluate AI responses using LLM-as-a-Judge models and human feedback.
Analyze AI answer quality, accuracy, and customer experience trends.
Partner with Engineering and Data Science teams to drive improvements.