SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salesforce is seeking an exceptional Software Architect to define and execute the long-term technical vision for Salesforce Developer Experience (DX)—transforming the platform from traditional human-in-the-loop tooling into an AI-native development ecosystem.
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. This is a hands-on role where you remain directly involved in engineering, not a documentation or review-board position.
Key responsibilities include:
**AI-Native Architecture & Multi-Agent Orchestration**: Lead the multi-year architectural evolution of Salesforce's developer platform. Architect stateful, multi-agent orchestration engines capable of decomposing complex features into executable tasks, generating code, handling dependencies, and self-correcting via runtime feedback. Define standardized interaction protocols (such as Model Context Protocol / MCP) and schema contracts to allow third-party AI agents, internal tools, and IDE extensions to interoperate seamlessly.
**Deep Integration with Salesforce Runtime & Metadata**: 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 hierarchies. Build real-time, high-precision retrieval architectures (RAG/graph-based code indexing) providing agents with semantic awareness of multi-million-line enterprise orgs. Redefine developer interfaces (CLI, DX Workspaces, Agentforce Vibes) so engineers can delegate, monitor, review, and collaborate with autonomous agents.
**Enterprise Trust, Security & Execution Guardrails**: Design isolated, ephemeral execution sandboxes for safely running AI-generated code and automated test suites. Establish deterministic evaluation and safety frameworks validating agent output—enforcing security compliance, static analysis, test coverage, zero-trust access, and governance rules. Implement fine-grained observability, audit logging, and provenance tracking for agentic modifications.
**Hands-On Building & System Optimization**: Write high-throughput production code (Java, Go, TypeScript, Python), author core SDKs, and build functional prototypes. Lead performance engineering initiatives minimizing agent context latency and optimizing vector/graph search over large codebases.
**Cross-Organizational Leadership**: Drive unified technical direction across AI Platform, Agentforce, Core Platform, Security, Trust, DevOps, and Runtime Infrastructure teams. Mentor senior architects and principal engineers, elevating engineering quality and fostering pragmatic innovation.
Required: 15+ years systems engineering experience designing and operating production-scale distributed systems. High proficiency in Java, Go, TypeScript, or Python with a track record of taking ambiguous concepts into production. Practical understanding of Salesforce metadata architectures, deployment models, and runtime frameworks (Apex, LWC). Hands-on experience with LLMs, AI agents, retrieval systems, tool calling, MCP ecosystems, evaluation frameworks, and multi-agent orchestration.
