AI / Agentic QE Engineer

About the RoleWe are hiring for our client for the role of AI / Agentic QE Engineer. This is a hands-on engineering role focused on testing and validating AI/LLM-based systems. The ideal candidate will have strong coding skills and practical experience working with GenAI applications, ensuring output quality, reliability, and performance in real-world scenarios. This is not a manual QA or coordination role.Key DetailsLocation: Mumbai, Bangalore, Hyderabad, Chennai, Indore, Bhopal, Gurugram, Noida Work Mode: Work From Office Experience: 5+ years Budget: ₹1.8 LPM Job Type: Contract Duration: 6 months (extendable) Key ResponsibilitiesBuild and execute automated test frameworks for AI/LLM-based systems Validate outputs of GenAI applications for correctness, consistency, and edge cases Analyze logs, responses, and datasets to identify patterns, failures, and issues Debug AI system behavior and contribute to improving system reliability Develop scripts for parsing data, logs, and APIs Contribute to test case generation workflows, including LLM-assisted approaches Collaborate with engineering teams to improve test coverage and system quality Required SkillsStrong hands-on coding skills (Python preferred) Ability to write scripts for data parsing, log analysis, and API testing Experience with test automation frameworks and API testing Practical experience working with GenAI / LLM-based systems Experience handling prompts, outputs, and validation workflows Strong problem-solving and logical thinking skills Ability to debug and analyze system behavior programmatically Nice to HaveExperience with RAG pipelines Exposure to vector search and embeddings Hands-on experience with agentic workflows Experience in prompt evaluation and hallucination detection Not a Fit IfPrimarily a manual tester with limited coding ability Experience with AI limited to using tools without hands-on implementation No experience with LLM outputs, validation, or workflow integration Unable to write scripts for processing data or logs Focused only on test documentation rather than automation What Success Looks LikeAbility to analyze raw outputs, logs, and datasets using code Capability to debug AI system behavior, not just report issues Comfortable working in evolving and uncertain AI environments Eligibility CriteriaCandidates must have a valid UAN number and LinkedIn profile Freelancers will not be considered Candidates available within 0–15 days preferred (up to 30 days for strong profiles) Strong alignment with the requirement Additional NotesOnly non-duplicated/exclusive profiles will be considered Candidates must be available for quick interview rounds Must be open to BOT round (if applicable)

Apply Now