Full Description

Full-Stack Developer — AI-Powered QA Automation Platform

**Location: ** Remote / Hybrid / office

**Type: ** Full-Time | Contract

**Experience: ** 3–6 Years

---

• About the Role

• We are building an AI-powered test automation platform that enables engineering and QA teams to generate, execute, and self-heal end-to-end browser test suites — without writing a single line of test code manually. The platform uses large language models to analyse web applications, understand their structure and user flows, and produce high-quality automated tests that run in the cloud.
• We are looking for a Full-Stack Developer with a genuine interest in QA automation, developer tooling, and applied AI. You will contribute across the full product — backend APIs, AI integration, browser automation, and the frontend dashboard.

---

• What You'll Work On

• Backend Engineering

• Design and maintain REST APIs that orchestrate long-running AI and browser automation jobs.

• Build async job pipelines for test generation, execution, and self-healing workflows.

• Integrate with LLM APIs (Anthropic Claude / OpenAI) to drive test generation and error analysis.

• Manage source ingestion from GitHub repositories and ZIP archives for code analysis.

• Work with async Python, relational databases, and background task workers.

• QA Automation & Browser Testing

• Develop and improve the Playwright-based test execution engine (headless and headed modes).

• Build the self-healing system that analyses test failures and automatically patches broken tests.

• Work with test result reporting, video capture, screenshots, and trace artifacts.

Handle complex browser scenarios: SPA routing, authentication flows, dynamic content, file uploads, and autocomplete widgets.

AI / Prompt Engineering

• Design and iterate on LLM prompts that produce reliable, production-quality Playwright TypeScript test code.

• Build context assembly pipelines that feed source code analysis and live DOM scan evidence to the model.

• Evaluate and improve output quality — reducing selector hallucinations, improving test coverage breadth, and handling edge cases in generated code.

• Frontend Development

• Build and maintain a React/TypeScript dashboard for managing projects, reviewing AI-generated tests, and viewing execution reports.

Create rich reporting UIs: test result breakdowns, embedded video playback, diff views, and real-time job status feeds.

• Implement a spec review and approval workflow before tests are committed and executed.

• DevOps & Infrastructure

• Deploy and maintain the application on cloud infrastructure (Azure / AWS / GCP).

• Manage web server configuration, process management, and environment setup.

• Contribute to CI/CD pipelines and GitHub integrations for committing generated test suites.

---

• Tech Stack

• | Layer | Technology |

|---|---|

| Backend | Python 3.11+, FastAPI, SQLAlchemy (async), Pydantic, Uvicorn |

| AI | Anthropic Claude API / OpenAI — prompt engineering, structured output |

| Test Automation | Playwright, TypeScript, @playwright/test |

| Frontend | React 18, TypeScript, Vite |

| Database | PostgreSQL / SQLite |

| Infrastructure | Azure / Linux, Nginx, systemd, GitHub Actions |

---

• Required Skills

• Python — 3+ years of professional backend development; async Python and REST API design.

• TypeScript / JavaScript — comfortable reading and writing Playwright test code and modern React components.

• Browser Automation — hands-on experience with Playwright, Cypress, or Selenium; knows how to debug flaky tests, handle dynamic content, and manage authentication states.

• React — experience building production SPAs with hooks, state management, and async data fetching.

• AI / LLM APIs — experience integrating with OpenAI, Anthropic, or similar; understands token limits, prompt structure, and parsing model output.

• REST API Design — clean, well-structured endpoints; understands async job patterns and polling.

• Git & GitHub — branching workflows, GitHub API usage, and CI/CD integration.

• Linux Fundamentals — comfortable on the command line; able to configure services, read logs, and debug server issues.

---

• Nice to Have

• Prior experience building developer tools, test infrastructure, or observability platforms.

• Understanding of how modern React/Vue/Angular SPAs behave at runtime — hydration, client-side routing, lazy loading.

• Experience with static analysis or AST parsing of frontend source code.

• Familiarity with GitHub Actions workflows.

• Cloud deployment experience (Azure, AWS, or GCP).

• Background in QA engineering — test planning, coverage strategy, or SDET experience.

---

• Responsibilities

• Take ownership of features from design through to deployment.

• Iterate on AI prompt quality and benchmark generated test output.

• Triage test execution failures and improve the automated healing system.

• Collaborate in a small, fast-moving team with direct access to product decisions.

• Write maintainable, well-documented code with appropriate test coverage.

• Participate in code reviews and contribute to engineering standards.

---

• How We Work

• Small team, high ownership — you shape what gets built, not just what gets assigned.

• Ship fast and iterate — we value working software over lengthy planning cycles.

• AI-first engineering culture — we use AI tooling throughout our own development workflow.

• Async-friendly and remote — no unnecessary meetings or rigid hours.

---

• What We Offer

• Competitive salary or contract rate based on experience and location.

• Fully remote with flexible working hours.

• Direct involvement in product and technical direction.

• A technically interesting problem space at the intersection of AI, testing, and developer tooling.

• Clear path to a senior or lead engineering role as the team grows.

---

• How to Apply

Please send the following to [saranya@radixlink.com]

1. A link to your GitHub profile or relevant portfolio.

2. A brief description (3–5 sentences) of a browser automation or testing project you have built or significantly contributed to.

3. Your availability and expected rate or salary.

• Shortlisted candidates will be invited to a 45-minute technical conversation — no take-home assignments.

---

• We are an equal opportunity employer. We welcome applications from candidates of all backgrounds and experience levels.