Salesforce Agentforce Architect

Key Responsibilities

· Own end-to-end solution architecture across Agentforce, Salesforce CPQ and Revenue Cloud Advanced.

· Architect agent-assisted and agentic workflows across opportunity, configuration, pricing, quoting, contracting, ordering and revenue lifecycle processes.

· Design agent orchestration patterns, including tool/function calling, workflow delegation, multi-agent patterns, state management and memory.

· Architect integration of Agentforce with Salesforce automation, Apex, Flow, APIs, MuleSoft and external enterprise services.

· Define appropriate use of LLMs, deterministic logic, workflow engines and traditional automation, rather than defaulting all use cases to generative AI.

· Design context engineering and retrieval strategies, including structured/unstructured grounding, retrieval depth, metadata filtering and relevance optimization.

· Establish secure agent action patterns using least-privilege access, guardrails, validation, approval checkpoints and human-in-the-loop mechanisms.

· Define AI evaluation frameworks covering answer quality, grounding, hallucination, task completion, tool selection, latency and business outcomes.

· Establish observability across agent reasoning paths, actions, integration failures, token/credit consumption and operational performance.

· Assess model and platform trade-offs across quality, latency, context window, cost, privacy and enterprise constraints.

· Architect resilient action layers and transactional integration patterns for revenue processes where consistency and recoverability are critical.

· Advise programs on consumption-based economics, AI credit/token optimization and architectural approaches to control run-time cost.

· Lead architecture reviews, design authorities and technical governance across global delivery teams.

· Mentor technical architects, developers and Agentforce specialists.

Required Technical Expertise

· Salesforce Agentforce and associated agentic architecture concepts.

· Salesforce CPQ and Revenue Cloud Advanced / Revenue Lifecycle Management.

· Salesforce Sales Cloud and core platform architecture.

· Agent orchestration and tool/function calling.

· Multi-agent architectures, delegation and coordination patterns.

· Agent state, short/long-term memory and session/context management.

· MCP and agent-to-agent interoperability concepts/patterns.

· RAG, semantic/vector search, embeddings, chunking and retrieval optimization.

· Context engineering beyond basic prompt engineering.

· Evaluation frameworks and AI observability.

· AI safety, grounding, guardrails and least-privilege action design.

· LLM model selection and architectural trade-offs.

· Classic NLP concepts including intent classification, entity extraction, semantic similarity and ranking.

· Apex, Lightning Platform, Flow, APIs and enterprise integration patterns.

· Strong understanding of asynchronous processing, transaction boundaries, resiliency, retries and idempotency.

· Security architecture including sharing, CRUD/FLS, permission models and data protection.

Preferred Qualifications

· 15+ years overall technology experience; 10+ years in Salesforce CPQ / Revenue Cloud architecture.

· Proven experience architecting enterprise CPQ / Quote-to-Cash implementations.

· Salesforce Application/System/Technical Architect credentials strongly preferred.

· Agentforce and Revenue Cloud-related certifications or demonstrable implementation experience.

· Experience with MuleSoft and large enterprise integration landscapes preferred.

· Ability to communicate architectural decisions to both engineering teams and senior business stakeholders.