Job Overview
Dun & Bradstreet is hiring a Senior Analyst - AI QA to validate AI agents, GenAI applications, and multi-agent workflows. The role focuses on AI quality engineering, Python automation, PySpark validation, RAG testing, AI safety, and ensuring enterprise AI systems are reliable, secure, and production-ready.
Dun & Bradstreet
5–8 Years
AI QA & Agent Testing
GenAI • LLMs • Python
Core Skills
Key Responsibilities
- Design AI testing strategies for LLM agents and GenAI workflows.
- Validate reasoning paths, tool calls, and multi-agent orchestration.
- Perform RAG validation, hallucination detection, and AI safety testing.
- Build Python and PySpark automation frameworks.
- Create reusable AI evaluation pipelines and testing utilities.
- Validate APIs, vector databases, and AI workflow integrations.
- Develop evaluation datasets and AI quality benchmarks.
- Collaborate with AI Engineering, Data Science, and Platform teams.
Required Skills
- 5–8 years of Software Engineering or AI QA experience.
- Strong Python and PySpark programming.
- Hands-on experience with LLMs and GenAI testing.
- Knowledge of LangGraph, CrewAI, AutoGen, and AI agent frameworks.
- Experience with RAG systems and AI workflow validation.
- API Testing and Cloud Platforms (AWS, Azure, GCP).
- CI/CD integration and automation testing.
- Strong analytical and communication skills.
Technology Stack
- Python
- PySpark
- LangGraph
- CrewAI
- AutoGen
- Vertex AI
- OpenAI Agents
- LangSmith
- LLMs
- RAG
- Vector Databases
- API Testing
- AWS
- Azure
- Google Cloud
- CI/CD
Why Apply?
Join Dun & Bradstreet's AI team to work on advanced AI agents, enterprise GenAI platforms, and next-generation AI automation systems. This role offers hands-on experience with LLM evaluation, RAG testing, multi-agent workflows, AI governance, and production-scale AI quality engineering.
Disclaimer: This job summary is published for informational purposes only. Please apply through the employer's official recruitment portal using the Apply button above.