Agentic QA & Reliability Engineer

Insight Global; Westlake (TX); On-site; USD 110,000 - 170,000; Full time

Job summary

Insight Global seeks a highly capable Full-Stack Agentic QA Engineer to transform ERP verification with AI-driven workflows. You will lead a QA Swarm testing UI, APIs, and financial processes, replacing manual tests with autonomous, self‑healing suites.

Build AI testing agents to explore, evaluate, and ensure 100% reliability in an autonomous environment. You will design, implement, and stress‑test verification pipelines, leveraging LLMs and modern tooling to guard production quality.

Qualifications

• Familiarity with LLMs and Agentic frameworks (OpenAI, Anthropic, LangChain/LangGraph).
• Strong hands‑on QA/SDET experience in UI test automation and API test automation.
• Hands on ability to build AI driven testing and verification workflows.
• Experience using Playwright for AI‑driven UI exploration.
• Proficiency with Python and SQL (Postgres or SQL Server).
• Knowledge of DSPy or other prompt‑optimization / evaluation frameworks.
• Background in red teaming, adversarial testing, or stress testing.
• Exposure to vector databases (pgvector, Qdrant) and RAG systems.
• Familiarity with data pipelines and orchestration tools (dbt, Airflow, Apache Hop).
• Experience with Docker, observability, or ML tooling (OpenTelemetry, Weights & Biases).
• Experience building AI Testing Agents i.e. Exploration Agents, Adversarial Agents.

Responsibilities

• Build and evolve an autonomous “QA Swarm” that tests the ERP UI, APIs, and financial workflows.
• Design AI agents that explore the product, find broken flows, and validate reconciliations.
• Replace brittle, manual tests with self‑healing, AI‑maintained test suites.
• Create Judge / Eval Agents to assess agent accuracy, hallucinations, and data safety.
• Reverse‑engineer legacy business logic and wrap it in modern, automated tests.
• Stress‑test systems using synthetic ERP data and adversarial scenarios.
• Act as the final gatekeeper of production reliability for agent‑driven features.

Skills

LLMs

Agentic frameworks

QA/SDET

Playwright

Python

SQL

Red teaming

Vector databases

Tools

OpenAI

Anthropic

LangChain/LangGraph

PostgreSQL/SQL Server

Docker

Airflow

dbt

OpenTelemetry

Weights & Biases

Job description

Job Description

You will join a specialized \"Modernization Strike Team\" focused on rewriting how enterprise software is built, tested, and operated using AI. We expect you to be a \"Full-Stack Agentic QA Engineer.\" You should be comfortable taking a complex business requirement and building an AI-driven verification workflow that ensures 100% accuracy. you are the guardian of reliability in an autonomous world. You aren't here to write manual test cases or maintain brittle Selenium scripts; you are here to build the QA Agents that explore, test, and verify our ERP while we sleep

Responsibilities Include

• Build and evolve an autonomous “QA Swarm” that tests the ERP UI, APIs, and financial workflows
• Design AI agents that explore the product, find broken flows, and validate reconciliations
• Replace brittle, manual tests with self‑healing, AI‑maintained test suites
• Create Judge / Eval Agents to assess agent accuracy, hallucinations, and data safety
• Reverse‑engineer legacy business logic and wrap it in modern, automated tests
• Stress‑test systems using synthetic ERP data and adversarial scenarios
• Act as the final gatekeeper of production reliability for agent‑driven features

Skills and Requirements

• Familiarity with LLMs and Agentic frameworks (OpenAI, Anthropic, LangChain/LangGraph)
• Strong hands‑on QA/SDET experience in UI test automation and API test automation
• Hands on ability to build AI driven testing and verification workflows
• Experience using Playwright for AI‑driven UI exploration
• Proficiency with Python and SQL (Postgres or SQL Server)
• Knowledge of DSPy or other prompt‑optimization / evaluation frameworks
• Background in red teaming, adversarial testing, or stress testing
• Exposure to vector databases (pgvector, Qdrant) and RAG systems
• Familiarity with data pipelines and orchestration tools (dbt, Airflow, Apache Hop)
• Experience with Docker, observability, or ML tooling (OpenTelemetry, Weights & Biases)
• Experience building AI Testing Agents i.e. Exploration Agents, Adversarial Agents

We are a company committed to creating diverse and inclusive environments where people can bring their full, authentic selves to work every day. We are an equal employment opportunity/affirmative action employer that believes everyone matters. Qualified candidates will receive consideration for employment without regard to race, color, ethnicity, religion, sex (including pregnancy), sexual orientation, gender identity and expression, marital status, national origin, ancestry, genetic factors, age, disability, protected veteran status, military or uniformed service member status, or any other status or characteristic protected by applicable laws, regulations, and ordinances. If you need assistance and/or a reasonable accommodation due to a disability during the application or the recruiting process, please send a request to [e-mail].