Mayank Saxena — Engineering Manager

I’m an AI Test Architect & Engineering Leader building LLM-powered, agentic systems to redefine software testing and quality engineering. With 16+ years in QA, automation, and engineering leadership, I’ve led large-scale SaaS quality initiatives. Today, my focus has shifted to solving a more important problem: 👉 How do we test systems that are intelligent, non-deterministic, and evolving? 🧠 What I’m Building I’ve designed and implemented a multi-agent LLM framework for API testing, enabling: • Automated generation of test cases from Swagger / requirements • Creation of automation-ready scripts using LLMs • Evaluation of coverage, accuracy, and gaps via AI evaluators • Iterative improvement through agent feedback loops This system moves QA from execution-heavy workflows to AI-driven, autonomous quality systems. ⚙️ Core AI/LLM Expertise • LLM-based Test Generation (prompt-driven + structured workflows) • Agentic AI Systems (multi-agent orchestration using LangGraph) • AI Evaluation (test coverage, correctness, hallucination detection) • API Testing (Swagger/OpenAPI → intelligent test design) • Automation Frameworks (Playwright, API automation pipelines) • QA Strategy for AI Systems (shift from deterministic → probabilistic testing) 🔍 What I’m Looking For I’m actively exploring roles where I can contribute as: • AI/LLM Architect (Testing / Quality Engineering) • LLM Evaluation Engineer / AI Quality Engineer • Agentic Systems Builder (Testing / Developer Productivity) 🎯 What I Bring to AI Teams • Strong foundation in engineering + quality systems at scale • Ability to translate AI capabilities into production-ready systems • Experience leading teams while building hands-on AI prototypes • Clear understanding of AI system risks: hallucinations, coverage gaps, evaluation challenges 🔥 Why This Matters As AI systems grow, traditional testing approaches break. The future lies in: ➡️ Evaluation over validation ➡️ Systems over scripts ➡️ Intelligence over execution And that’s exactly where I’m focused. 🤝 Let’s Connect If You’re Working On • LLM applications / GenAI platforms • AI evaluation, guardrails, or safety • Agent-based systems • AI-driven developer or QA tooling

Stackforce AI infers this person is a SaaS QA Architect with expertise in AI-driven testing solutions.

Location: Delhi, India

Experience: 15 yrs 10 mos