Lead Software Engineer - Enterprise Agents

Salesforce · California - San Francisco

hybridfull-time6-10 years

posted 1d

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. Lead Software Engineer — Enterprise Agents (Specialty Requirement) IN SCHOOL OR GRADUATED WITHIN THE LAST 12 MONTHS? PLEASE VISIT FUTURE FORCE FOR OPPORTUNITIES Join our team building enterprise-grade AI Agents headed for GA in the coming months. We need a strong all-round software engineer who also brings deep, hands-on experience in production Agent architecture — someone who can operate across the full stack while specializing in Agent systems that enterprise customers rely on at scale. Your Impact: You'll own the architecture and delivery of production Agent capabilities under real GA timeline pressure — balancing speed with the reliability, security, and observability enterprise customers expect, while also contributing broadly across our backend and platform codebase. As part of this role, you will: Architect, design, implement, test, and deliver production-grade software systems — including Agent capabilities built for scale and enterprise reliability Write high-quality, maintainable, well-tested code across services, APIs, and data layers, not just Agent-facing components Design orchestration patterns where AI Agents integrate into human and system workflows securely and predictably Build and maintain the shared system context — the explicit repository of design constraints, guardrails, and standards that keeps Agent behavior accurate and reliable in production Drive the technical path to GA: define readiness criteria, close architecture gaps, and de-risk the timeline Debug, troubleshoot, and resolve complex issues across the stack, from infrastructure to application logic Critically evaluate code and Agent behavior (human- or AI-generated) for correctness, security, and performance Participate in on-call rotation to keep services operational and highly available Mentor others on both general software engineering practices and Agent architecture patterns Present designs to internal/external stakeholders and review the designs of others Collaborate cross-functionally with product, design, and other engineering teams to ship end-to-end features Required Skills: A related technical degree, or equivalent hands-on experience 8+ years of professional software development experience, including production experience architecting and shipping Agent-based systems Strong computer science fundamentals: data structures, algorithms, distributed systems, and API/service design Deep knowledge of object-oriented programming and proficiency in at least one OOP language (Java, JavaScript, C++, C#, Ruby, Python) Solid experience with databases (SQL/NoSQL), REST/GraphQL API design, and building scalable, secure backend services Familiarity with cloud infrastructure, CI/CD pipelines, and modern software delivery practices Proven experience with Agent orchestration frameworks, tool-calling patterns, and LLM integration in production environments Strong understanding of the reliability, security, and observability requirements unique to enterprise-grade Agent systems (guardrails, evaluation, monitoring, failure handling) Demonstrated AI-first engineering approach — fluent use of AI tools (Claude Code, GitHub Copilot, Codex