Senior Quality Engineer Agentic AI & Autonomous Testing

Job Description: Senior Quality Engineer Agentic AI & Autonomous Testing Locations: Jaipur, Noida, Gurgaon, Pune, Bengaluru, Hyderabad Duration: 3-6 Months Contract with possible extension Experience: 10+ Years Role Overview We are seeking a Senior Quality Engineer (QE) with deep hands-on expertise in Agentic AI and Autonomous Testing systems to lead the next generation of quality engineering. This role goes beyond traditional automation to design, build, and operate intelligent QA agents capable of independently planning, executing, analyzing, and optimizing testing workflows across enterprise applications. The ideal candidate will combine strong QE foundations, AI/ML understanding, and engineering rigor to build self-learning test ecosystems that improve coverage, reduce manual effort, and enable continuous quality at scale. This role is critical for establishing an AI-first QE capability where agents act as autonomous testers, quality guardians, and optimization engines embedded across the SDLC. --- Key Responsibilities 1. Agentic AI Testing Architecture & Development Design and build autonomous QA agents capable of: Test discovery, generation, execution, and maintenance Failure diagnosis and root cause analysis Self-healing and adaptive test strategies Develop agent architectures using LLMs, workflows, and orchestration layers (e.g., sense decide act learn loop) Define agent goals, constraints, and reasoning logic to enable independent decision-making in testing workflows Implement multi-agent ecosystems (test generation agents, validation agents, monitoring agents) --- 2. Autonomous Test Strategy & Execution Build end-to-end autonomous testing frameworks that: Generate test cases from requirements, APIs, and production data Explore systems dynamically to uncover edge cases and untested paths Maintain and optimize test suites through continuous learning Design behavior-driven evaluation systems (not just assertion-based testing) Implement AI-driven regression, exploratory, and risk-based testing models Enable self-healing and adaptive execution to reduce maintenance overhead --- 3. AI Validation, Evaluation & Observability Build evaluation frameworks for non-deterministic AI systems: Behavior-based validation (vs exact output matching) LLM-as-judge scoring frameworks Semantic and structured validation approaches Define and monitor AI-specific quality metrics: Accuracy, reliability, hallucination rates, drift, safety Implement continuous validation and observability pipelines Establish governance controls, auditability, and quality gates for AI-driven testing --- 4. QE Platform Engineering & Integration Integrate agentic testing into CI/CD pipelines and DevOps workflows Build scalable AI-enabled automation frameworks across: Web, mobile, API, and backend systems Enable closed-loop learning systems where agents improve based on execution data Collaborate with engineering to embed quality as code / quality as platform --- 5. AI-Driven Quality Transformation Drive transition from: Script-based automation agent-based autonomous testing Manual validation intelligent quality orchestration Define enterprise QE strategy for AI adoption (agent-first testing model) Introduce capabilities such as: AI-generated test assets Predictive defect detection Automated failure triage and clustering Act as SME for Agentic QA practices, tools, and frameworks --- 6. Collaboration & Stakeholder Engagement Partner with: Engineering, Product, Data, Architecture, Business Translate business requirements into autonomous test strategies Drive cross-functional alignment on quality, risk, and governance Mentor teams on AI-driven QA practices and agent development --- Required Skills & Experience Core QE & Engineering 1012+ years in Quality Engineering / Test Automation Deep expertise in: Automation frameworks (Selenium,WebdriverIO, Maestro, Cypress, etc.) API testing, performance testing, and integration validation Strong programming skills (Python, Java, JavaScript, or C#) --- Agentic AI & Autonomous Testing (Must-Have) Proven experience building or working with: AI testing agents / autonomous testing systems LLM-based workflows, prompt engineering, and reasoning systems Hands-on with: AI-driven test generation, self-healing frameworks, or adaptive testing Understanding of agent capabilities: Perception, reasoning, planning, execution, feedback loops --- AI/ML & Data Competency Working knowledge of: Machine learning concepts, NLP, embeddings, RAG Experience designing: Evaluation metrics and scoring systems for AI outputs Familiarity with: Data pipelines, model validation, and drift detection --- Modern QE & DevOps Experience integrating testing into: J