Software Engineering Lmts

Salesforce Salesforce · Enterprise · Bellevue, WA

Salesforce is seeking a Lead Software Engineer for their Analytics Agent team to build next-generation AI-powered analytics with agentic experiences. The role involves designing and orchestrating scalable agentic systems, integrating AI agents into human workflows, and collaborating on generative AI products. Candidates need expertise in LLMs and agents, strong programming skills, and experience with modern software development practices.

What you'd actually do

  1. 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.
  2. Design and orchestrate scalable, high-performance agentic systems — accounting for throughput, latency, parallel processing, stream processing, and asynchronous I/O — where AI agents integrate seamlessly into human workflows.
  3. Collaborate with product managers, engineers, and researchers to rapidly iterate on generative AI products and prototypes, shaping user experiences through context engineering and LLM capabilities.
  4. 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.

Skills

Required

  • expertise shaping experiences with LLMs and agents
  • proficiency in evaluating model performance
  • defensive error handling
  • streaming data optimization
  • caching
  • explainability to probabilistic systems
  • strong programming skills in Python, Java, or similar languages
  • experience building full-stack applications
  • developing, scaling, and maintaining production-grade distributed systems
  • experience with modern software development practices
  • DevOps principles
  • cloud-based deployments
  • event-driven architectures
  • queues
  • message buses
  • Critically evaluate code (human or AI-generated) for correctness, quality, security, and performance
  • A related technical degree required

Nice to have

  • experience using AI tools (e.g., Claude Code, GitHub Copilot, Codex, Cursor, etc.) in development workflows
  • advanced prompt engineering skills
  • ability to write precise, structured prompts
  • cultivate the system context that makes AI outputs reliable, secure, and production-ready
  • demonstrated, genuine AI-first approach to engineering

What the JD emphasized

  • agentic systems
  • evaluating model performance
  • Critically evaluate code (human or AI-generated)

Other signals

  • agentic systems
  • generative AI products
  • LLM capabilities