பணி விளக்கம்

About the Role

Helika creates AI-driven characters and publishing tooling for entertainment brands and game studios, designed to help them connect with players directly in the communities where those players already interact. The team is hiring a QA Generalist who truly cares about what gets released and is comfortable taking end-to-end ownership of product quality. This position combines classic software testing with validation of AI and LLM-powered features, making it a particularly important role in the product team.

Key Responsibilities

Take ownership of product quality by defining the overall testing approach and deciding when automation is worthwhile, when manual checks are enough, and when production monitoring should handle the risk.
Join grooming, planning, and sprint meetings as an active contributor who identifies risks early and raises the difficult questions before development begins.
Share risk assessments clearly with engineers, product managers, and other stakeholders, including the ability to justify a release hold when needed and explain the reasoning convincingly.
Rank defects by business effect and risk rather than simply logging every issue, and help the team distinguish urgent fixes from items that can safely wait.
Validate AI agents and LLM-based capabilities, including prompt behavior, hallucination detection, regression checks, and edge-case coverage in agent-style workflows.
Work with observability platforms such as LangSmith, LangFuse, or similar tools to trace agent behavior, analyze prompt quality, and spot production issues.
Carry out functional, regression, exploratory, and UI/UX testing for the web product.
Perform API testing through tools such as Postman, Swagger, or custom scripts, and investigate failures independently instead of relying on a developer for every issue.
Review usability, accessibility, and performance concerns, acting as the final quality checkpoint before users see the product.
Suggest and lead improvements to QA practices, release processes, and the team’s overall quality mindset.

Requirements

At least 5 years of QA experience, with direct responsibility for product quality.
Strong understanding of how to test AI and LLM features, including the fact that small prompt changes can alter behavior and that model outputs need evaluation rules.
Excellent manual testing skills and experience using test design methods, with good judgment on when to investigate freely, follow a structured plan, or keep things lightweight.
Hands-on API testing ability, including reading logs, querying data, and diagnosing issues without assistance.
Good understanding of SDLC and Agile ways of working, with sprint ceremonies seen as useful collaboration rather than overhead.
A risk-based mindset that focuses on impact, avoids blocking releases for minor cosmetic problems, and supports clear go/no-go decisions.
Ability to produce practical QA documentation such as test plans, test cases, and bug reports that genuinely help the team.
English proficiency at B1 level or above in both writing and speaking.

Preferred Experience

Exposure to LangSmith, LangFuse, or other LLM evaluation and observability platforms.
Python automation experience, including the ability to design, build, and maintain tests.
Experience creating evaluation datasets and defining scoring criteria for AI-generated outputs.
Familiarity with AWS, GCP, and related cloud tools and services.
Experience working as the only or main QA person on a product team.

Benefits

Fully remote work arrangement.
Flexible working schedule.
Paid leave that includes 15 working days of vacation plus 5 extra days off each year.
Public holidays based on your local country calendar.
Opportunities for career growth.
A lean, results-focused environment with minimal bureaucracy and real flexibility.
Pay that matches your experience and expectations.

Additional Information

This position is based in Germany and is offered as a full-time remote role.

QA Generalist