£595 Per day
Inside
Hybrid
England, United Kingdom
Summary: The AgentForce Tester role is focused on validating AI-powered digital capabilities within a secure public sector environment, specifically on the Salesforce AgentForce platform. The position requires a dedicated tester to ensure the accuracy, reliability, and compliance of intelligent agents through structured testing methodologies. The role involves collaboration with product, engineering, and business stakeholders to ensure optimal performance across real-world use cases. Candidates should possess a strong background in software testing, particularly in AI systems, and be comfortable working in a regulated setting.
Key Responsibilities:
- Designing and executing structured test plans for AI agents within the AgentForce environment.
- Testing conversational flows, APIs, integrations, CRM interfaces, and multi-channel deployments.
- Validating intent recognition, response quality, business rule adherence, and safety guardrails.
- Conducting regression testing after retraining, fine-tuning, or configuration updates.
- Logging reproducible defects and working closely with engineers to validate fixes.
- Analysing conversation logs to identify misclassifications, edge cases, and optimisation opportunities.
- Monitoring metrics such as accuracy, latency, escalation rates, and user satisfaction.
- Supporting compliance, audit readiness, and responsible AI standards in a regulated setting.
Key Skills:
- Proven experience in software testing, QA, or conversational AI testing.
- Exposure to functional, regression, exploratory, and UAT methodologies.
- Understanding of AI or LLM-based systems, chatbot testing, or NLP concepts.
- Working knowledge of JSON, APIs, and automation frameworks.
- Strong analytical capability with attention to detail.
- Experience in agile delivery environments.
- Highly desirable: Experience with Salesforce AgentForce, Agent Builder, or AgentForce Testing Centre.
- Exposure to Einstein or similar AI agent platforms.
- Experience in secure or regulated environments.
Salary (Rate): £595 daily
City: London
Country: United Kingdom
Working Arrangements: hybrid
IR35 Status: inside IR35
Seniority Level: Mid-Level
Industry: IT
AgentForce Tester
Level: Mid–Senior
Location: London, Remote First (1–2 days per month onsite max)
Function: AI Testing / Quality Assurance
Industry: Public Sector
Rate: £575–£595 per day
Clearance: SC Clearable
Contract: 6 Months (High Extension Potential)
About the Role
Our client is delivering AI-powered digital capabilities within a secure public sector environment. They are building and scaling intelligent agents on the Salesforce AgentForce platform and need a dedicated Tester to ensure these agents are accurate, reliable, safe, and production-ready. This is not traditional UI testing. You will be validating AI behaviour, conversational accuracy, workflow logic, integrations, and compliance standards. You will sit between Product, Engineering, and business stakeholders to ensure agents perform as intended across real-world use cases.
What You’ll Be Doing
- Designing and executing structured test plans for AI agents within the AgentForce environment.
- Testing conversational flows, APIs, integrations, CRM interfaces, and multi-channel deployments.
- Validating intent recognition, response quality, business rule adherence, and safety guardrails.
- Conducting regression testing after retraining, fine-tuning, or configuration updates.
- Logging reproducible defects and working closely with engineers to validate fixes.
- Analysing conversation logs to identify misclassifications, edge cases, and optimisation opportunities.
- Monitoring metrics such as accuracy, latency, escalation rates, and user satisfaction.
- Supporting compliance, audit readiness, and responsible AI standards in a regulated setting.
Ideal Background
You will demonstrate:
- Proven experience in software testing, QA, or conversational AI testing.
- Exposure to functional, regression, exploratory, and UAT methodologies.
- Understanding of AI or LLM-based systems, chatbot testing, or NLP concepts.
- Working knowledge of JSON, APIs, and automation frameworks.
- Strong analytical capability with attention to detail.
- Experience in agile delivery environments.
- Highly desirable: Experience with Salesforce AgentForce, Agent Builder, or AgentForce Testing Centre.
- Exposure to Einstein or similar AI agent platforms.
- Experience in secure or regulated environments.
Keywords that will stand out: AgentForce, Agent Builder, Testing Centre, AI Agent QA.
What You’ll Receive
- £575–£595 per day.
- Remote-first model with minimal London travel.
- 6-month initial contract with strong likelihood of extension.
- Exposure to AI transformation work within a high-impact government department.
Who Should Apply
This role suits a technically strong QA professional who understands AI systems beyond surface-level testing. You are structured, detail-driven, comfortable working with ambiguity, and capable of challenging agent outputs where logic or safety is compromised. You must be SC clearable and a sole British national. Non-cleared profiles may be considered if technically strong. If your background includes AgentForce Builder or Testing Centre experience, flag this clearly when applying. Interested candidates should respond with availability and confirmation of clearance status.