AI SDET
Role details
Job location
Tech stack
Job description
We are seeking a AI Software Development Engineer in Test (SDET) to ensure the quality, reliability, and trustworthiness of AI-powered applications. This role is automation-first and focuses heavily on validating AI behavior, verifying data correctness, and ensuring system reliability across backend services, data pipelines, Retrieval-Augmented Generation (RAG) systems, and AI agents. You will work closely with AI, machine learning, data, and platform engineering teams, with guidance and support from senior quality leadership., * Design, build, and maintain robust automated tests for backend services, APIs, and AI-enabled systems
- Validate end-to-end AI workflows, including data inputs, retrieval logic, and generated outputs
- Test RAG systems by verifying source data quality, retrieval accuracy, and response correctness
- Perform data verification to ensure the accuracy of summarized, derived, and feature-level data used by AI systems
- Validate AI behavior for consistency, edge cases, regressions, and failure scenarios
- Identify data anomalies, drift, and pipeline issues impacting AI outputs and collaborate on resolution
- Integrate automated tests into CI/CD pipelines and contribute to quality metrics and reporting
- Support performance, reliability, and scalability testing for AI-driven services
Requirements
Do you have experience in Quality assurance within IT?, * Strong experience as an SDET or Automation Engineer with a focus on backend and service-level testing
- Proficiency in test automation using one or more programming languages (TypeScript, Java, C#, or Python)
- Strong experience with API testing and distributed systems validation
- Solid understanding of data validation concepts including accuracy, consistency, and completeness
- Strong SQL skills
- Hands-on experience using SQL and/or programmatic checks to validate data used by applications or AI systems
- Experience integrating automated tests into CI/CD pipelines
- Ability to translate requirements and expected AI behavior into reliable, repeatable automated tests
Nice to Have
- Experience testing AI/ML systems, RAG pipelines, or LLM-based applications
- Familiarity with testing non-deterministic systems and defining effective test oracles
- Experience validating data drift, model regressions, or AI behavior changes over time
- Familiarity with Playwright, Postman, or similar testing frameworks
- Experience working with data-intensive platforms or analytics systems
- Background in healthcare or other regulated environments
- Interest in leveraging AI-assisted testing techniques to improve coverage and efficiency