QA Engineer - Agentic Memory Testing

We are looking for a QA Engineer to validate agent memory capabilities within an enterprise AI Agent Platform being built from the ground up. The role will focus on ensuring that AI agents reliably retain, retrieve, and manage contextual information across both individual conversations and multiple sessions.

You will test stateful and personalized agent behaviors, memory extraction and retrieval, lifecycle controls, and regression scenarios to ensure that memory improves agent performance without introducing incorrect or irrelevant context.

About the Client

Our client is a large global enterprise operating across multiple markets, with a complex technology landscape and a strong focus on digital transformation and innovation. The organization is actively investing in modern cloud, data, and AI capabilities to enable scalable, secure, and highly automated solutions across its business.

About the Project

The project is focused on building an enterprise-grade AI Agent Platform from the ground up. The platform will provide a standardized foundation for developing, deploying, orchestrating, securing, and observing AI agents across multiple teams and use cases.

The initiative covers the full agent lifecycle and brings together agent orchestration, observability, security, governance, integrations, evaluation, and platform engineering. Engineers joining the project will have an opportunity to influence key architectural and technical decisions and contribute to a new platform rather than maintaining an existing solution.

Responsibilities

• Design and execute functional tests for short-term and long-term agent memory.
• Validate in-session context continuity and cross-session memory recall.
• Test memory extraction strategies to ensure that summaries, facts, and preferences are captured correctly.
• Validate memory retrieval to ensure agents retrieve relevant context while filtering irrelevant information.
• Test memory lifecycle behaviors, including TTL expiration, deletion, and namespace isolation.
• Develop Python-based automated tests for agent memory workflows and API-driven services.
• Perform regression testing to ensure memory changes do not negatively affect agent response quality.
• Validate stateful agent behaviors including context retention and personalization.
• Test memory isolation to prevent inappropriate context sharing between users, sessions, or agents.
• Validate user deletion and privacy-related memory workflows.
• Integrate memory testing into broader agent quality and regression suites.
• Collaborate with AI and platform engineers to identify memory-related defects and improve agent reliability.

Qualifications

Skills

• Agent memory functional testing - short-term memory (in-session continuity), long-term memory (cross-session recall)
• Memory extraction validation - verify Summary and Semantic strategies extract correct facts/preferences
• Memory retrieval testing - validate agents retrieve relevant context, filter irrelevant memories
• Memory lifecycle testing - TTL expiration, user deletion, namespace isolation
• Agent regression testing - verify memory does not degrade agent response quality
• Python test automation for memory workflows

Experience

• 4+ years QA engineering for AI/ML or conversational AI systems
• Testing stateful agent behaviors (context retention, personalization)
• Functional test automation for API-driven services
• Regression testing methodologies

Nice to have

• Agent memory framework testing (LangChain, LangGraph)
• Conversational AI evaluation
• AWS AgentCore Memory testing
• GDPR compliance testing (user deletion validation)

Perks and Benefits

• Flexible work schedule.
• Fixed financial bonus issued upfront on a quarterly basis, covering the average market price of private medical care and sport card - B2B contract.
• Present on the occasion of birthday, wedding, child birth.
• E-learning accounts for Coursera, O'Relly, Udemy.
• Corporate language school.