Agentforce Architect

Why Join AspenView?

• At AspenView, we’re more than a nearshore IT partner, we’re a people-first, purpose-driven company that believes great culture drives great outcomes. We’re passionate about connecting talent and technology to deliver measurable value for clients, and meaningful career paths for our people.

About the Role

We are seeking an Agentforce Architect to own the design of a North American client’s: which processes get an agent, how agents are bounded and grounded, how they hand off to humans, and how the whole estate is governed. Agentic architecture is a new discipline and confidence in it is still thin across the ecosystem, so this role is expected to establish the patterns and the governance rather than inherit them.

This is a full-time, contractor agreement, remote position delivered from AspenView’s Latin American delivery centres, working the client’s core business hours with substantial time-zone overlap. You will work as part of the client’s squad under AspenView Delivery Leadership, to whom this role reports. This is a contributor role, not a task-execution role: the team needs someone who questions whether the right thing is being built, and says so.

Success in this role means agents in production have defined boundaries, evaluation suites and audit trails; use-case selection is deliberate, with documented reasoning for rejected use cases; deflection and quality metrics exist before launch, not after the first complaint; and client leadership treats you as the authority on what agents should and should not do.

What You Will Do
Agentic Architecture

• Decide which business processes warrant an agent, which warrant deterministic automation, and which warrant neither.
• Design agent topology, including agent boundaries, topic decomposition, action inventories, and escalation paths.
• Design the grounding architecture across Data 360, knowledge, and retrieval sources.

Trust and Governance

• Define the guardrail standard covering authorization for actions, PII handling, injection defense, and audit trail.
• Establish the evaluation and release standard an agent must meet before it faces customers.
• Own the human-in-the-loop design, including when an agent must stop and hand over.

Delivery and Advisory

• Guide the AI and data engineers building the agents, and review what they produce.
• Advise executive stakeholders on realistic scope, cost, and deflection expectations.
• Set the measurement model: containment, resolution quality, and cost per interaction.

Platform Integration

• Design how agents sit alongside existing Service Cloud, Sales Cloud, and integration architecture.
• Own the consumption-cost architecture for Agentforce and its Data 360 dependencies.

What You Bring

Education

• Bachelor’s degree in Computer Science, Software Engineering, or a related field, or equivalent experience.

Experience

• 8+ years in solution or technical architecture, including hands-on delivery of production LLM or agentic systems.
• Demonstrated experience taking an agentic use case from concept to production with measured outcomes.
• Ability to say which use cases will not work, including to an executive who wants them to.

Technical Expertise

• Agentforce architecture: Agent Builder, topics and actions, Prompt Builder, Einstein Trust Layer, and Atlas reasoning.
• Salesforce Data 360: Deep expertise using Data 360 as a grounding and retrieval layer.
• Service Cloud and Sales Cloud: Process design expertise, since that is where most agents land.
• AI safety and evaluation: Guardrails, red-teaming, regression evaluation, and observability practice.

Certifications

• Salesforce Certified AI Specialist plus Application or System Architect (strongly preferred).

Language Proficiency

• Professional English, with the ability to run requirement and design conversations directly with North American stakeholders.