AI Automation Quality Engineer

Harvarduniversity; Cambridge (MA); On-site; USD 110,000 - 180,000; Full time

Job summary

Harvard University is seeking an AI Automation Quality Engineer to pioneer intelligent, autonomous QA for the my.harvard portal. You will design agents that read Jira stories, architecture docs, and business rules to generate comprehensive test scenarios across functional, API, and accessibility domains, while collaborating with analysts and developers.

Ideal candidates have strong Python and Django/FastAPI experience, along with hands-on familiarity with Playwright, Selenium, and CI/CD.

Qualifications

• 2+ years of post-secondary education or relevant work experience.
• Proficient Python development and automated testing experience.
• Experience with Django and FastAPI web applications.
• Familiar with Playwright, Selenium, Cypress, pytest, or similar tools.
• Strong Jira and Agile process knowledge.
• Understanding of Git workflows and CI/CD pipelines.
• Experience with LLMs, prompt engineering, and AI-assisted software development.
• Knowledge of retrieval-augmented generation (RAG), embeddings, and vector DBs.

Responsibilities

• Lead AI-driven QA strategy for the Harvard portal and beyond.
• Design AI agents to generate functional, integration, regression, accessibility, and API tests from requirements and docs.
• Build code-aware testing by analyzing Django/FastAPI/frontend codebases.
• Develop RAG pipelines leveraging Jira, Confluence, Git repos, API specs, and defect history.
• Establish human-in-the-loop validation with BAs and Product Owners before automation.
• Produce maintainable automated tests using Playwright, Selenium, pytest; prepare PRs.
• Capture feedback to improve prompts, testing patterns, and agent performance.

Skills

Python

Test automation

Django

FastAPI

Playwright

Selenium

pytest

Jira

CI/CD

LLMs

RAG

AI testing

Git

Agent frameworks

Education

Two years post-secondary education

Tools

GitHub Copilot

LangGraph

CrewAI

AutoGen

Semantic Kernel

Pinecone

pgvector

Chroma

Weaviate

OpenTelemetry

Job description

Job-Specific Responsibilities:

The AI Automation Quality Engineer leads the next generation of quality engineering for the my.harvard portal, moving beyond traditional QA to design intelligent, agent-based testing capabilities that automatically analyze requirements, understand application code, generate reusable test assets, and continuously improve HUIT's testing strategy.

This role combines strong software testing experience with modern AI engineering concepts, including Retrieval-Augmented Generation (RAG), large language models (LLMs), agentic workflows, and test automation frameworks. Working closely with Business Analysts, developers, and product owners, the AI Automation Quality Engineer helps build an autonomous QA platform that accelerates delivery while improving software quality.

AI-Powered Test Generation: Design and implement AI agents that read Jira user stories, acceptance criteria, architectural documentation, and business rules to automatically generate comprehensive functional, integration, regression, accessibility, and API test scenarios

Code-Aware Testing: Build agents capable of analyzing Django, FastAPI, and frontend codebases to understand application behavior, identify impacted components, and generate reusable test cases with high coverage

RAG & Knowledge Engineering: Develop Retrieval-Augmented Generation (RAG) pipelines that leverage Jira, Confluence, Git repositories, existing test suites, architecture documentation, API specifications, and historical defects to improve test quality and reduce hallucinations

Human-in-the-Loop Validation: Implement workflows where generated test scenarios are reviewed and validated by Business Analysts and Product Owners before automation code is produced

Autonomous Test Automation: After approval, generate maintainable automated tests using Playwright, Selenium, pytest, or equivalent frameworks, validate results, and prepare commits or pull requests for inclusion in the shared test repository

Continuous Learning: Capture review feedback, production defects, and failed test patterns to improve prompts, retrieval strategies, reusable testing patterns, and agent performance over time

Quality Engineering: Maintain regression suites, API tests, UI automation, performance validation, and CI/CD integration while ensuring generated tests remain reliable and maintainable

Collaboration: Partner with developers, architects, BAs, and DevOps engineers to define AI-driven quality engineering standards and governance

Basic Qualifications:

Basic Qualifications are the minimum threshold a candidate must meet in order to be considered for this role.

Minimum of two years' post-secondary education or relevant work experience

Additional Qualifications and Skills:

Required:

• 3+ years building automated test frameworks for enterprise web applications
• Strong Python development experience
• Experience testing Django and/or FastAPI applications
• Experience with Playwright, Selenium, Cypress, pytest, or similar frameworks
• Experience using Jira and Agile development processes
• Understanding of Git workflows and CI/CD pipelines
• Experience working with LLMs (OpenAI, Anthropic, Gemini, etc.), prompt engineering, and AI-assisted software development
• Understanding of Retrieval-Augmented Generation (RAG), embeddings, vector databases, MCP, or agent frameworks such as LangGraph, CrewAI, AutoGen, Semantic Kernel, or similar
• Strong analytical thinking and ability to translate business requirements into automated quality strategies
• Knowledge of advanced IT project management principles (e.g. Agile) and software
• Knowledge of SDLC and STLC

The following qualifications are strongly preferred. If you meet some, but not all, you are still encouraged to apply; we value employees with a willingness to learn.

• Experience developing AI agents that generate code or software tests
• Experience integrating AI into SDLC workflows
• Knowledge of GitHub Copilot, Cursor, Claude Code, Windsurf, or similar AI development environments
• Experience with vector databases (Pinecone, pgvector, Chroma, Weaviate)
• Experience with OpenTelemetry, observability, and evaluation frameworks for AI systems
• Experience in higher education or enterprise ERP/student information systems
• Knowledge of Oracle, REST APIs, GraphQL, Docker, Kubernetes, and cloud-native development
• Experience measuring test coverage, mutation testing, and AI quality metrics
• AI/ML engineering and agentic system design
• Test automation and quality engineering best practices
• Cross-functional collaboration with Business Analysts, developers, and product owners
• Strong analytical thinking and problem-solving
• Demonstrated team performance skills, service mindset approach, and the ability to act as a trusted advisor
• Continuous improvement and adaptability to emerging AI and testing technologies

Certificates and Licenses:

Completion of Harvard IT Academy specified foundational courses (or external equivalent) preferred

Working Conditions:

Onsite work is performe