Senior/Lead Automation Tester in Python (Agentic Memory Testing)

EPAM Systems Inc; United States; Remote; USD 110,000 - 150,000; Full time

Job summary

EPAM Systems Inc seeks a Senior/Lead Automation Tester in Python to own functional and regression test suites for agent memory behavior within an Enterprise Agent Development Platform. You will design and execute tests for short-term and long-term memory, validate memory extraction, and build Python automation for memory workflows on AWS.

Requirements include 3+ years in QA for AI/ML or conversational AI, experience testing stateful agents, API testing, and GDPR-focused validation, with strong

Qualifications

• 3+ years of QA engineering experience in AI/ML or conversational AI systems.
• Experience testing stateful agent behaviors including memory retention.
• Background in functional test automation for API-driven services.
• Knowledge of regression testing methodologies.
• Proficiency in English at a B2+ level.

Responsibilities

• Own functional and regression test suites for agent memory behavior.
• Design and execute tests for short-term and long-term memory across sessions.
• Validate memory extraction to ensure correct facts and preferences are captured.
• Conduct memory retrieval testing to verify relevant context is used.
• Perform memory lifecycle testing (TTL expiration, user deletion, namespace isolation).
• Run agent regression testing to ensure memory quality does not degrade responses.
• Build Python test automation for memory workflows.

Skills

Python

Test automation

QA engineering

AI/ML testing

Memory testing

API testing

Regression testing

English proficiency

Tools

AWS

LangGraph

LangChain

Job description

We are looking for a Senior/Lead Automation Tester in Python to own functional and regression test suites for agentic memory behavior within an Enterprise Agent Development Platform — a production-grade, cloud-native ecosystem that enables engineering teams to define, orchestrate, deploy, and observe AI agents at scale. The platform standardizes agent development across the organization using LangGraph and Strands Agents on AWS AgentCore Runtime, spanning agent framework design, runtime architecture, marketplace integration, CI/CD automation, and enterprise-grade observability — reducing agent development from months to days while enforcing consistent security, quality, and governance standards.

Responsibilities

• Own functional and regression test suites for agentic memory behavior
• Design and execute agent memory functional tests covering short-term memory (in-session continuity) and long-term memory (cross-session recall)
• Validate memory extraction to verify Summary and Semantic strategies extract correct facts and preferences
• Conduct memory retrieval testing to validate agents retrieve relevant context and filter irrelevant memories
• Perform memory lifecycle testing, including TTL expiration, user deletion, and namespace isolation
• Run agent regression testing to verify memory does not degrade agent response quality
• Build Python test automation for memory workflows

Requirements

• 3+ years of experience in QA engineering for AI/ML or conversational AI systems
• Experience testing stateful agent behaviors, including context retention and personalization
• Background in functional test automation for API-driven services
• Knowledge of regression testing methodologies
• Proficiency in English at a B2+ level
• Nice to have Experience testing agent memory frameworks (LangChain, LangGraph)
• Background in conversational AI evaluation
• Familiarity with AWS AgentCore Memory testing
• Knowledge of GDPR compliance testing (user deletion validation)