Python jobs in United States

Dry Ground AI is seeking a Quality Engineer – AI, Software, & Automation Solutions to serve as the technical owner of product quality across all AI, automation, and software solutions delivered to clients. This role requires a deeply technical professional who can understand, test, and validate every component of our architecture. This includes front-end applications, agentic AI systems, workflow automations, backend services, integrations, voice interfaces, and data pipelines.

This is not a traditional QA position. The expectation is that this person will build, improve, and automate the entire quality function. They will use AI-enhanced development tools, create automated test harnesses, design diagnostic utilities, and implement intelligent systems that help Dry Ground AI scale internally using the same technologies we deploy for clients.

The ideal candidate is a builder with strong engineering instincts, a systems thinker who can test complex multi-layer AI behavior, and a professional who can collaborate across engineering and engagement teams to ensure that deliverables meet the highest standard before being presented to clients.

Develop QMS (Quality Management Systems) framework for internal and external solutions.

Develop comprehensive test plans across front-end, backend, automation, and AI layers.

Validate application logic, agent workflows, API integrations, prompt quality, and error handling.

Test AI agent behavior for reliability, consistency, safety guardrails, and edge case scenarios.

Build automated test suites where appropriate using modern frameworks and AI tools.

Evaluate human-in-the-loop workflows, reasoning path visibility, and agent state transitions.

Create internal automation tools that support quality checks, regression testing, and consistency validation.

Build utilities that monitor AI output correctness and detect drift or prompt failure patterns.

Implement automated validation for large-scale workflows such as n8n, Make, custom automations, and model-driven tasks.

Design intelligent alerting systems that surface issues early in the development cycle.

Use AI coding platforms like Cursor and Claude Code to improve velocity and maintain high quality in test development.

Build LLM-assisted testing scripts and automated evaluation harnesses for generative AI features.

Work with engineering to integrate AI into QA processes such as automated prompt scoring and conversational flow validation.

Contribute to the refinement of prompts, agent instructions, and reasoning frameworks from an accuracy and reliability perspective.

Partner with engineering to define acceptance criteria and ensure all work is testable and observable.

Coordinate closely with the engagement manager to ensure project readiness and identify risks before client delivery.

Communicate test findings clearly with actionable remediation guidance.

Serve as the final technical quality gate on all deliverables.

Establish Dry Ground AI’s QA standards and continuously improve them as we scale.

Create reusable testing templates and systems for use across all client projects.

Analyze recurring issues and lead efforts to resolve root causes.

Drive a culture of technical excellence and reliability throughout the engineering team.

5 or more years in a highly technical QA, SDET, or full-stack engineering role.

Strong engineering fundamentals across JavaScript, TypeScript, Python, React, and API driven applications.

Experience testing AI-enabled products, conversational interfaces, or complex automation workflows.

Ability to build automated testing systems using tools such as Playwright, Cypress, or custom frameworks.

Experience with AI-enhanced development tools such as Cursor, Github, and Claude Code.

Strong understanding of prompt behavior, LLM variability, and common failure patterns.

Comfort working across the entire stack, including cloud services, APIs, vector databases, and real-time systems.

Excellent communication skills for coordinating across engineering and client-facing teams.

Experience with agentic AI frameworks, voice AI systems, or workflow automation tools such as n8n and Make.

Experience implementing testing strategies for RAG systems, embedding workflows, and vector search pipelines.

Familiarity with CI pipelines that run automated quality checks and AI-based evaluation tests.

Experience in consulting environments with direct ownership of client-facing deliverables.

Competitive compensation and performance incentives.

Remote-first work environment.

Opportunity to influence the architecture, reliability, and technical quality of AI systems across multiple industries.

A culture that prioritizes innovation, high standards, and the use of AI to scale operations.