Thesis: Can AI Agents Replace the Tester? Comparing LLM Browser Agents and Scripted End-to-End Tests (AI Testing)

Location: Onsite at the hirify.global office in Sundsvall, Sweden. Start date: January or March 2027.

Company

hirify.global is a strategic partner in product and digital service development, formed through the combination of Semcon and Knightec.

What you will do

• Set up one or two open-source web applications as test subjects, preferably in a regulated domain.
• Build and compare scripted end-to-end tests with LLM-based agents that navigate, click, type, and read a real web browser.
• Create and inject a controlled catalogue of 30–50 realistic faults covering functional logic, input validation, authorization, data integrity, and UI/usability.
• Evaluate scripted baseline, free exploration, persona-driven exploration, and specification-guided exploration.
• Compare at least two LLMs, including a larger capable model and a smaller cheaper model.
• Measure bug detection, false alarms, reproducibility, resilience to UI changes, maintenance effort, and total cost over time.

Requirements

• Bachelor’s or Master’s degree in Computer Science, Software Engineering, or a related field.
• Graduation in June 2027.
• Fluency in Swedish, both written and spoken.
• Fluency in English, both written and spoken.

Culture & Benefits

• Hands-on thesis work with real projects in a supportive and innovative environment.
• Opportunity to develop practical skills in AI-driven testing, browser automation, and software quality evaluation.
• Thesis placement at the Sundsvall office with a start in January or March 2027.

Hiring process

• Submit the application through the careers page; applications are accepted until 2026-11-30.
• Applications are not accepted by email due to GDPR requirements.