From 2025 to 2026, hands-on working in the AI - Agentic Development Environment (ADE) utilising Claude code and GitHub Copilot.
AI Quality Engineering Leader focused on Agentic AI, LLM Reliability, and Scalable Quality Engineering for AI products.
I design, build, and validate AI QA agents for dev, stage and production environments, combining hands-on engineering with team leadership.
- Layer 1 - Local Developer Agents: Validate developer builds in the early stage, run pre-merge checks, and enforce shift-left quality gates.
- Layer 2 - QA Agents: Generate and maintain tests, execute intelligent regression, and validate workflows across UI, API, and LLM paths.
- Layer 3 - Vendor Agents (On Demand): Use specialized external agents for deep analysis, performance spikes, and targeted quality audits.
- Agentic quality frameworks for LLM, RAG, multimodal, and MCP-based systems
- Evaluation pipelines for accuracy, groundedness, safety, latency, and cost
- AI-assisted test creation with human-in-the-loop controls and synthetic data strategies
- Multi-agent orchestration for autonomous QA, release validation, and incident triage
- Security testing for AI systems: prompt injection, jailbreaks, data leakage, and abuse cases
- Agentic AI Quality: agent evaluation, tool-call reliability, memory and workflow validation
- AI/LLM Testing: prompt robustness, bias checks, groundedness checks, guardrail validation
- RAG and LLMOps: retrieval quality, evaluation datasets, observability, and continuous evals
- Test Automation: Playwright, Cypress, Selenium, API, contract, and integration testing
- Programming: Python, TypeScript, JavaScript, Java
- Performance and Security: k6, JMeter, OWASP ZAP, Burp Suite, AI red-teaming
- Cloud and Platform: AWS, Azure, Docker, Kubernetes, GitHub Actions, CI/CD
- Governance and Compliance: risk controls, auditability, and responsible AI quality practices
- Leadership: engineering management, QA strategy, KPI ownership, stakeholder communication
- Agent Reliability Engineering
- AI Test Architecture, Evaluation Operations (LLMOps), and Governance
- Shift-Left and Continuous Quality for AI products and agent workflows
- Legacy-to-modern automation framework migration
- Scalable quality operations for fast-release teams
- Quality metrics for AI product readiness and production monitoring
- AI QA Engineer
- Agent Reliability Engineer
- AI Test Architect
- AI Quality Engineer (LLMOps / AgentOps)
- SDET (AI and Cloud)
- Staff / Principal QA Engineer (AI Systems)
- Test Engineering Lead
- Engineering Manager - Quality and AI
padmaraj nidagundi at gmail.com