Software Engineering Mts - Full-stack/agentic AI Engineer

Salesforce Salesforce · Enterprise · San Francisco, CA +1

Salesforce is seeking a Software Engineering MTS - Full-Stack/Agentic AI Engineer to join their Agentforce team. The role involves architecting, designing, and shipping scalable full-stack applications on the Agentforce platform, building and iterating on AI agent tooling using modern agentic frameworks and LLM-backed workflows, and designing systems where AI agents integrate into human workflows. The candidate should have deep OOP knowledge (Java or Python), full-stack experience (React/TypeScript, APIs, backend services), and hands-on experience with agentic platforms, prompt engineering, RAG, and tool/function calling.

What you'd actually do

  1. Architect, design, and ship scalable full-stack applications on the Agentforce platform — owning everything from backend API and data modeling to polished, responsive UI experiences
  2. Build and iterate on AI agent tooling using modern agentic frameworks and LLM-backed workflows, contributing to platform-level multi-agent systems and interaction patterns
  3. Build and ship high-quality, production-grade software using modern engineering practices, with AI as a core part of your development workflow by pushing the boundaries of AI development tools to deliver secure, optimized, and high-quality code
  4. Design and orchestrate complex systems where AI agents integrate seamlessly into human workflows, driving efficiency and innovation at scale

Skills

Required

  • OOP (Java or Python)
  • Fullstack ability
  • UI (React/TypeScript)
  • APIs
  • Backend services
  • Agentic platforms (Agentforce, LangChain, AutoGen, CrewAI, or similar)
  • Prompt engineering
  • RAG patterns
  • Tool/function calling
  • Generative AI applications
  • AI-first approach to engineering
  • AI tools (e.g., Claude Code, GitHub Copilot, Cursor)
  • Technical degree

Nice to have

  • Multi-agent interaction
  • Task planning
  • LLM orchestration
  • Building UI that surfaces AI-generated content
  • Streaming responses
  • Agent traces
  • Tool call visualization
  • Model evaluation
  • Agent observability
  • LLM output quality frameworks
  • Agile/TDD practices
  • Supporting production customer escalations

What the JD emphasized

  • agentic frameworks
  • LLM-backed workflows
  • multi-agent systems
  • AI agents integrate seamlessly into human workflows
  • agentic platforms
  • prompt engineering
  • RAG patterns
  • tool/function calling
  • generative AI applications
  • AI-first approach to engineering
  • AI tools
  • multi-agent interaction
  • task planning
  • LLM orchestration
  • AI-generated content
  • agent observability
  • LLM output quality frameworks

Other signals

  • shipping fullstack features alongside ML engineers
  • build and iterate on AI agent tooling
  • platform-level multi-agent systems
  • AI agents integrate seamlessly into human workflows