About this role
Role Overview
Strong understanding of GenAI system architecture, including Retrieval-Augmented Generation (RAG) and Agent-based systems, with hands-on experience in implementing Python-based AI evaluation frameworks such as Ragas, DeepEval, and similar tools. Proven ability to perform Model and Agent quality evaluations using platforms like Arize, LangFuse, and Confident AI, while driving Responsible AI (RAI) validation and reporting key RAI metrics. Experienced in golden dataset curation, synthetic dataset generation, and establishing AI observability and tracing through OpenTelemetry (OTEL) instrumentation to enable effective monitoring, diagnostics, and continuous quality improvement of AI systems.
Key Responsibilities
- Ability to develop AI Assurance test strategy to assess AI systems for quality, safety, reliability and responsible AI behavior
- Design AI evaluation strategy for LLMs, RAG and agent evaluation across functional and non-functional dimensions
- Experience in Golden dataset curation & Synthetic dataset generation
- Experience in implementing AI evaluation frameworks like Ragas, DeepEval, etc.
- Experience in using AI Evaluation tools like LangSmith, Arize, Langfuse, Galileo, Evidently, etc.
- Experience in instrumentation to establish AI Observability / tracing using OTEL libraries
- Experience in Integrating AI evaluation into CI/CD pipeline
- Experience in Responsible AI validation
Required Skills and Capabilities
- Strong understanding of GenAI System Architecture of RAG & Agents
- Proficiency in Python & AI evaluation SDKs
- AI Evaluation Frameworks (Ragas, DeepEval)
- Model Evaluation
- Agent Evaluation
- Responsible AI (RAI) Validation
- RAI Metrics Reporting
- Golden Dataset Curation
- Synthetic Dataset Generation
- AI Observability
- AI Tracing
- OpenTelemetry (OTEL)
- LLM Evaluation
- AI Quality Engineering
- AI Governance
- AI Monitoring
- AI Testing & Assurance
- Root Cause Analysis (AI Systems)
- Knowledge of regulatory considerations for AI systems
Role-Specific Requirements
- Proficiency in Python & AI evaluation SDKs
- Strong understanding of RAG & agentic system architecture
- Ability to develop AI Assurance test strategy to assess AI systems for quality, safety, reliability and responsible AI behavior
- Design AI evaluation strategy for LLMs, RAG and agent evaluation across functional and non-functional dimensions
- Experience in Golden dataset curation & Synthetic dataset generation
- Experience in implementing AI evaluation frameworks like Ragas, DeepEval, etc.
- Experience in using AI Evaluation tools like LangSmith, Arize, Langfuse, Galileo, Evidently, etc.
- Experience in instrumentation to establish AI Observability / tracing using OTEL libraries
- Experience in Integrating AI evaluation into CI/CD pipeline
- Experience in Responsible AI validation
- Knowledge of regulatory considerations for AI systems
Experience Requirements
More than 4 years of experience in AI Assurance Testing