Software Architect - AI-Native Developer Platform (Salesforce DX)

To get the best candidate experience, please consider applying for a maximum of 3 roles within 12 months to ensure you are not duplicating efforts.

Job Category

Software Engineering

Job Details

About Salesforce

Salesforce is the #1 AI CRM, where humans with agents drive customer success together. Here, ambition meets action. Tech meets trust. And innovation isn’t a buzzword — it’s a way of life. The world of work as we know it is changing and we're looking for Trailblazers who are passionate about bettering business and the world through AI, driving innovation, and keeping Salesforce's core values at the heart of it all.

Ready to level-up your career at the company leading workforce transformation in the agentic era? You’re in the right place! Agentforce is the future of AI, and you are the future of Salesforce.

About the Team

The Salesforce Developer Experience (DX) organization is building the future of enterprise software development.

Our mission is to make Salesforce the easiest enterprise platform to build on—not only for human developers, but also for autonomous AI agents. We are transforming traditional developer tooling into an AI-native development platform spanning IDEs, intelligent coding agents, CLI, APIs, DevOps, enterprise governance, evaluation frameworks, and cloud-native infrastructure.

We build products including Agentforce Vibes, DX Workspaces, Salesforce CLI, DevOps Center, platform APIs, developer services, and the foundational capabilities that power millions of developers and the next generation of AI-assisted software delivery.

The Role

We're looking for an exceptional Architect with deep engineering experience to help define and execute the long-term technical vision for Salesforce DX.

This is not a documentation or review-board architecture role. You will design and build high-throughput systems, write production-quality code, prototype frontier concepts, and establish how AI agents safely modify enterprise software at scale. You will partner across engineering leadership, Distinguished Engineers, product management, AI research teams, and platform organizations to solve complex technical problems around developer productivity, AI agents, enterprise trust, and software lifecycle automation.

Key Responsibilities

Define AI-Native Developer Architecture & Multi-Agent Orchestration

• Lead the multi-year architectural evolution of Salesforce’s developer platform from traditional human-in-the-loop tooling to autonomous software engineering ecosystems.

• Architect stateful, multi-agent orchestration engines capable of decomposing complex features into executable engineering tasks, generating code, handling dependencies, and self-correcting via runtime feedback loops.

• Define standardized interaction protocols (such as Model Context Protocol / MCP) and schema contracts to allow third-party AI agents, internal platform tools, and external IDE extensions to seamlessly interoperate with Salesforce services.

Deep Integration with Salesforce Runtime & Metadata Ecosystem

• Bridge modern LLM capabilities with Salesforce architectures, designing abstractions that allow agents to reason over complex org metadata, dependency graphs, Apex execution models, and LWC component hierarchies.

• Build real-time, high-precision retrieval architectures (RAG/graph-based code indexing) that provide agents with full semantic awareness of multi-million-line enterprise orgs, including custom fields, business logic, security permissions, and schema variations.

• Redefine developer interfaces (Salesforce CLI, DX Workspaces, Agentforce Vibes) so human engineers can delegate, monitor, review, and collaborate with autonomous agents within unified workflows.

Build Enterprise Trust, Security & Execution Guardrails

• Design isolated, ephemeral execution sandboxes capable of safely executing AI-generated code, running automated test suites, and performing dynamic analysis without risk to production metadata or enterprise data boundaries.

• Establish deterministic evaluation and safety frameworks to validate agent output—enforcing security compliance, static code analysis, unit test coverage, zero-trust access control, and governance rules before code merge.

• Implement fine-grained observability, audit logging, and provenance tracking for agentic modifications t