Job Description

Core Skills & Experience:

Hands-on experience with Salesforce Agentforce and conversational AI frameworks.
Strong understanding of prompt engineering, reasoning engines, and orchestration layers.
Experience with Salesforce Data Cloud, including data ingestion, harmonization, identity resolution, and activation.
Familiarity with observability tools and performance monitoring for AI systems.
Experience integrating third-party platforms and enterprise data systems via APIs.
Ability to analyze data insights and translate them into actionable improvements.
Strong communication and collaboration skills across cross-functional teams.

Key Success Criteria:

Proven expertise in Salesforce LLMs, prompt engineering, and agent orchestration.
Hands-on experience with Apex, APIs, and scalable integration patterns.
Strong understanding of Data Cloud architecture, data modeling, and real-time data activation.
Knowledge of secure data practices, compliance frameworks, and ethical AI principles.
Ability to influence cross-functional decisions and contribute to architecture strategy.
Experience with test automation frameworks (e.g., RAGAS, DeepEval) and QE collaboration.

Data & Knowledge Engineering:

Work with structured and unstructured data across enterprise systems and Salesforce Data Cloud.
Design and manage data pipelines including ingestion, transformation, and harmonization.
Integrate knowledge articles, knowledge graphs, vector databases, and unified customer profiles.
Enable secure data access with robust data governance, masking, and PII protection mechanisms.
Leverage Data Cloud for real-time data activation to power intelligent agent responses.

Agent & Prompt Development:

Design and optimize execution flows, prompts, and agent actions using Apex and APIs.
Utilize Agent Builder and Prompt Builder to create scalable, reusable agent solutions.
Collaborate on modeling strategies leveraging Salesforce LLMs, foundation models, and domain-specific models.
Integrate Data Cloud insights into agent workflows for contextual and personalized interactions.
Deploy and manage LLMs on cloud platforms such as Databricks and OpenAI.

Trust, Compliance & Security:

Ensure adherence to enterprise compliance standards and regulatory requirements.
Implement monitoring mechanisms for toxicity, bias detection, and auditability.
Maintain secure data handling practices across Agentforce and Data Cloud environments.
Enforce authentication, authorization, and MFA standards across systems.

Collaboration & Influence:

Partner with Lead Engineers, Solution Architects, and Integration Architects.
Influence non-functional requirements (NFRs) including scalability, performance, and security.
Contribute to technical solution design documents (TSDs) and roadmap planning.
Support QE teams by enabling automation-first testing strategies.

Enablement & Lifecycle Management:

Follow the Agentforce lifecycle: Ideate → Setup → Configure → Test → Deploy → Monitor.
Contribute to internal knowledge sharing, documentation, and onboarding initiatives.
Continuously improve implementation practices and contribute to the Agentforce playbook.