Senior Automation Tester - Python, Agentic AI & LLM Systems

Job Description

Senior Automation Tester (Python) – Agentic AI & LLM Systems

Location: Glasgow (Hybrid – 3 days per week on‑site)
Start Date: Immediate
Right to Work: Must have full UK working rights (no sponsorship available due to start dates)
Additional Requirement: Must have 3 years of UK address history due to immediate onboarding
Programme: AI / Agentic AI

Seniority: Senior Automation Engineer

Overview

We are seeking a Senior Automation Engineer / SDET with strong Python skills and hands‑on experience testing AI systems, including LLM‑driven applications and agentic AI workflows. You will design and build a scalable automation frameworks, implement modern AI testing strategies, and ensure the quality and reliability of next‑generation conversational and agent‑based AI products.

This role is ideal for someone who is passionate about automation engineering and has a solid understanding of how AI/LLM systems behave in real‑world scenarios.

Key Responsibilities

• Develop and maintain a Python‑based automation framework for validating AI agents (chatbots, voicebots, agentic workflows).
• Design and execute automated tests for:
  • LLM responses
  • Conversational flows
  • Retrieval‑augmented generation (RAG)
  • End‑to‑end agentic scenarios
• Apply modern AI testing strategies and evaluation methods (e.g., DeepEval, RAGAS — beneficial but not essential).
• Integrate automated tests into CI/CD pipelines (Jenkins, GitHub Actions, Azure Repos).
• Build and manage batch and scheduled executions using Docker, Kubernetes, cron jobs, or similar tooling.
• Manage code repositories using Git, including branching strategies, version control, and collaborative workflows.

·  Collaborate closely with engineering, AI/ML, and product teams to ensure high‑quality delivery of AI‑powered features.

Required Skills & Experience

• Strong Python development skills, particularly for automation (PyTest preferred).
• Solid background in test automation and framework design.
• Experience testing or validating AI/LLM‑based systems (agentic workflows, conversational AI, RAG pipelines, etc.).
• Understanding of AI evaluation concepts — familiarity with tools like DeepEval or RAGAS is a bonus, not a requirement.
• Experience implementing CI/CD pipelines and automated batch executions.
• Strong understanding of source code management, Git workflows, and collaborative engineering practices.
• Ability to design structured, scalable, and maintainable automation solutions.

Preferred Qualities

• Quick learner with a proactive, ownership‑driven mindset.
• Strong problem‑solving skills and ability to work in fast‑moving AI environments.
• Comfortable collaborating with cross‑functional teams (AI/ML, engineering, product).
• Passion for AI technologies and modern testing methodologies.

Qualifications

Additional Information