This list contains only the countries for which job offers have been published in the selected language (e.g., in the French version, only job offers written in French are displayed, and in the English version, only those in English).
The AgentForce Automation Tester is responsible for ensuring the quality and performance of AI agents built on the AgentForce platform. This role involves designing and executing test plans, conducting manual and automated testing, and collaborating with developers and stakeholders to enhance agent performance.
Job Responsibility:
Design, execute, and document test plans and test cases for AI agents within the AgentForce environment
Conduct manual and automated testing across conversational flows, integrations, API calls, and user journeys
Validate agent accuracy, intent recognition, response quality, safety, and adherence to business rules
Perform regression testing following updates, fine‑tuning, or retraining cycles
Test agents across various channels (e.g., web, mobile, CRM interfaces, chat widgets)
Log defects clearly with reproducible steps and diagnostics
Collaborate with engineering teams to troubleshoot issues and validate fixes
Identify gaps in requirements, edge cases, and potential failure points
Analyse conversation logs to detect errors, misclassifications, and optimisation opportunities
Monitor agent performance metrics such as accuracy, latency, handoff rates, and user satisfaction
Provide feedback and insights to improve training data, prompts, and system configuration
Ensure agents meet organisational standards for security, data handling, and responsible AI practices
Validate that responses avoid prohibited content and meet safety guardrails
Support audits and documentation related to testing coverage and release readiness
Work closely with Product, Engineering, and Business SMEs to align testing with functional requirements
Contribute to the development of testing frameworks, automation tools, and best practices
Participate in sprint ceremonies and cross‑functional working groups
Requirements:
Proven experience in software testing, QA, or conversational AI testing
Familiarity with testing methodologies (functional, regression, exploratory, UAT)
Experience with AI/ML concepts, LLM‑based systems, or chatbot testing (preferred)
Understanding of JSON, APIs, and test automation frameworks
Strong analytical skills with the ability to identify inconsistencies and patterns
Excellent communication skills and attention to detail
Ability to work in agile environments and manage multiple priorities
Nice to have:
Experience with Salesforce AgentForce, Einstein, or similar AI agent platforms
Knowledge of prompt engineering, training data quality, or NLP
Experience working with secure or regulated environments
What we offer:
Tailored benefits that support your physical, emotional, and financial wellbeing