Middle General QA

Required Skills:

• Possessing 3+ years of dedicated professional experience in quality assurance and automation engineering, demonstrating a strong track record of successful project contributions.
• Demonstrated advanced proficiency in Quality Assurance methodologies and practices, ensuring high standards of software reliability and performance.
• Possessing intermediate hands-on experience in QA Automation, including the design, development, and maintenance of automated test suites for web applications and REST APIs.
• Strong working knowledge and intermediate-level experience with Python programming for scripting, test automation, and data analysis.
• A foundational understanding and beginner-level exposure to Artificial Intelligence concepts, including LLM output evaluation, with an eagerness to explore its applications in QA.

Preferred Skills:

• Familiarity with Amazon Web Services at a beginner level, particularly Lambda, SQS, RDS and CloudWatch in the context of test environments or automation pipelines.
• Experience testing applications with Japanese-language content or interfaces is a plus.

Job Responsibilities

• Define and own the evaluation framework for AI features, including transcription accuracy, summary quality and needs categorization metrics
• Validate real-time Japanese speech-to-text in live consultation sessions, covering streaming stability, speaker separation and handling of background noise
• Build a ground truth data set together with the client domain experts and use it to score AI-generated consultation summaries and identified needs
• Verify relevance of support service recommendations returned by knowledge base search, including location-based results and map display
• Test the asynchronous processing pipeline (API Gateway, SQS, Lambda), confirming correct retries, error handling and dead letter queue behaviour
• Verify authentication and role-based access through Amazon Cognito
• Check that personal data is stored and handled according to APPI requirements, including region restrictions and access to session records
• Design test cases for edge scenarios (interrupted sessions, poor audio quality, long consultations, incomplete resident data)
• Perform integration and regression testing across the frontend, backend, and AI pipeline for each release
• Support client validation sessions and prepare test reports for stakeholder review

Department/Project Description

We are building an AI-powered social prescribing platform for municipal social welfare departments in Japan, developed in collaboration with Hitachi and Niigata University. Community social workers currently record resident consultations manually and search for suitable local support services by themselves, which takes significant time and depends on individual experience. The platform records the consultation, transcribes Japanese speech in real time, generates a structured summary, identifies the resident’s needs and recommends relevant local services and facilities with their location on a map. The architecture is built on AWS (React frontend, Python FastAPI on ECS, Lambda and SQS for asynchronous processing, RDS PostgreSQL, Amazon Transcribe, Amazon Bedrock with Claude models, AWS Location Service). The first release is delivered, and the team is extending the platform with new features based on municipal feedback.