Senior Backend Engineer, Salesforce

• You have 6+ years experience designing and building large scale, distributed backend systems
• You have experience with API design, versioning, and building systems that many teams build on top of
• You have strong skills in at least one modern programming language and experience shipping production code
• You can reason clearly about ambiguous, large scale systems and communicate tradeoffs to a team
• You have a demonstrated, genuine AI first approach to engineering, using AI tools (such as Claude Code, GitHub Copilot, Codex, or Cursor) to move faster, build fluency across the stack, and contribute well beyond your core specialty
• You have advanced prompt engineering skills and the ability to write precise, structured prompts, cultivating the system context that makes AI outputs reliable, secure, and production ready
• You have a related technical degree

Desirable

• The Experience The Agentic Setup team builds AI agents, on a skills based architecture, that turn expert only, multi step product configuration, Org troubleshooting and management into natural language, agent assisted workflows
• As part of this team, you will work across agent runtime, capability and skill design, evaluation infrastructure, and the systems that let agents find and act on the right data
• We are looking for a Lead Software Engineer to help us build agentic experiences for product setup and configuration
• You will help design a core agent framework, contribute to a growing skills ecosystem, and build the evaluation infrastructure that keeps agent behavior trustworthy as it scales
• This role is based in San Francisco
• You'll join a team building intelligent systems that automate the repetitive, elevate the strategic, and power better decisions at scale
• Design and build a core agent framework that hosts many specialized capabilities, orchestrates sub tasks reliably, and integrates seamlessly into human workflows
• Define the contract for reusable agent skills, focusing on API design, versioning, and composability so many teams can build and contribute consistently
• Build evaluation infrastructure that measures agent quality even when outputs are non deterministic, and use that signal to catch regressions over time
• Help agents efficiently find the right records and context using structured queries, catalogs, and semantic search
• Build and ship high quality, production grade software using modern engineering practices, with AI as a core part of your development workflow, pushing the boundaries of AI development tools to deliver secure, optimized, and high quality code
• Contribute to building and maintaining the shared system context, an explicit repository of system designs, constraints, and standards that enables AI to operate accurately and reliably
• Critically evaluate code, human or AI generated, for correctness, quality, security, and performance