Agentic AI Developer

Position: Agentic AI Developer

Location: McLean, VA

Duration: 6-Month Contract (Potential Extension)

Job Description:

We are seeking an experienced Agentic AI Developer to design and build next-generation AI-powered software quality engineering solutions. This role will focus on developing reusable GenAI-driven testing frameworks, intelligent automation agents, quality governance standards, and AI-assisted reporting that can be adopted across multiple engineering teams. The ideal candidate will have strong expertise in LLM-based agent development, GitHub automation, test automation frameworks, and CI/CD engineering, with the ability to build scalable solutions that improve software quality and accelerate development.

Key Responsibilities:

Agentic AI Test Automation:

• Design and develop reusable AI-powered test automation frameworks and reference implementations for multiple engineering teams.
• Build intelligent agents that assist with:
• Automated test generation from requirements, APIs, contracts, and schemas.
• Test maintenance through selector updates, contract validation, and flaky test detection.
• Failure analysis using log correlation, root cause identification, and automated defect creation.
• Establish standardized testing architecture covering UI, API, integration, and service-layer testing.

Testing Standards & Quality Governance:

• Define enterprise-wide testing standards and quality best practices.
• Develop reusable templates for:
• Test plans
• Test cases (including Gherkin-style specifications)
• Definition of Ready (DoR)
• Definition of Done (DoD)
• Create scalable tagging and metadata strategies to improve reporting, traceability, and quality gates.
• Define risk-based testing strategies and minimum coverage requirements across applications and services.

GenAI-Powered Reporting & Analytics:

• Build automated reporting pipelines that aggregate testing results across multiple microservices and CI/CD pipelines.
• Integrate test execution data, service health metrics, logs, traces, and defect information into centralized reporting.
• Develop AI-generated insights including:
• Release readiness summaries
• Failure clustering and trend analysis
• Change impact analysis
• Commit and pull request correlation
• Produce dashboards, markdown reports, and CI artifacts for engineering leadership and development teams.

AI-Based Quality Gates:

• Develop intelligent review agents that validate user stories and requirements before development begins.
• Automate checks for:
• Acceptance criteria completeness
• Missing functional requirements
• Data dependencies
• Environment readiness
• Privacy and security considerations
• Edge cases and ambiguity detection
• Integrate automated quality gates into GitHub workflows, pull requests, and CI/CD pipelines to reduce rework and improve software quality.

Required Qualifications:

• Bachelor's degree in Computer Science, Software Engineering, or a related technical field.
• Experience developing GenAI or LLM-powered applications with multi-step reasoning and tool-using agents.
• Strong understanding of prompt engineering, structured outputs (JSON schemas), evaluation techniques, and AI guardrails.
• Experience designing AI workflows for automated testing, requirements validation, reporting, and software engineering productivity.
• Strong hands-on experience with GitHub Copilot and GitHub engineering workflows.
• Deep expertise with:
• GitHub Actions
• CI/CD automation
• Pull Request workflows
• Branch protection
• CODEOWNERS
• GitHub APIs and automation
• Advanced experience with automated testing frameworks including:
• Karate for API testing
• Playwright for UI automation
• Strong understanding of:
• API testing
• Contract testing
• Integration testing
• UI automation
• Test data management
• Test isolation
• Parallel execution strategies
• Experience aggregating testing results across distributed microservices and multiple CI/CD pipelines.
• Strong knowledge of software quality engineering best practices, risk-based testing, and test coverage strategies.

Preferred Qualifications:

• Experience building enterprise AI automation platforms.
• Knowledge of observability tools, logging platforms, and distributed tracing.
• Experience with software quality metrics, release governance, and engineering productivity initiatives.
• Familiarity with Agile development methodologies and DevOps practices.
• Experience creating reusable engineering frameworks and developer enablement tools.

Mindlance is an Equal Opportunity Employer and does not discriminate in employment on the basis of – Minority/Gender/Disability/Religion/LGBTQI/Age/Veterans.