Software Engineering Smts/lmts

Salesforce Salesforce · Enterprise · Hyderabad, India, India

Salesforce is seeking a Senior Member of Technical Staff (SMTS) / Lead Member of Technical Staff (LMTS) for their AI Services team to design and build AI agents and automation infrastructure. The role involves creating intelligent agents that reason, plan, use tools, and execute multi-step workflows for tasks like automated test generation, failure triage, and codebase analysis. The team also builds the agent orchestration layer, an AI Quality Readiness scoring platform, and an agent contribution ecosystem. The role requires strong software engineering experience, experience building AI agents, and understanding of developer tooling and CI/CD.

What you'd actually do

  1. Design and build AI agents from the ground up: define their goals, tool access, context strategies, planning approaches, and evaluation criteria
  2. Create specialized agents for quality and productivity workflows (dev orchestration, test authoring, code review, failure triage, validation strategy, codebase migration)
  3. Build the agent orchestration layer that coordinates multiple agents into reliable, end-to-end workflows with handoffs, retries, and human-in-the-loop checkpoints
  4. Build and scale the AI Quality Readiness scoring platform that measures how prepared teams are for AI-first development: code structure, documentation quality, test patterns, Second Brain / Project Brain configuration, and repository health
  5. Instrument, evaluate, and iterate on agent performance using production usage data, automated evals, and feedback loops

Skills

Required

  • 7+ years of software engineering experience building production systems at scale
  • Strong proficiency in Java, Python, or TypeScript
  • Experience building AI agents or agentic systems (structured prompting, tool use, multi-step reasoning, context management)
  • Solid understanding of software testing, CI/CD pipelines, and developer tooling
  • Track record of designing systems that operate reliably in large-scale, multi-tenant environments
  • Ability to break down ambiguous problems into iterative, shippable increments
  • Ability to drive adoption across engineering teams through quality of tooling and developer experience

Nice to have

  • Experience building developer productivity tools or internal platforms used broadly across an engineering organization
  • Experience with large-scale test infrastructure, test selection, or test generation systems
  • Experience building scoring, metrics, or code intelligence systems
  • Familiarity with static analysis, linting infrastructure, or developer insight tooling
  • Background in quality engineering, test automation, or DevOps
  • Experience working in large enterprise codebases with complex build and deployment systems

What the JD emphasized

  • design and build AI agents
  • intelligent agents that reason, plan, use tools, and execute multi-step workflows autonomously
  • build the agent orchestration layer
  • AI Quality Readiness scoring platform
  • agent contribution ecosystem
  • Instrument, evaluate, and iterate on agent performance
  • Experience building AI agents or agentic systems

Other signals

  • AI agents
  • automation infrastructure
  • intelligent agents
  • reason, plan, use tools, and execute multi-step workflows autonomously
  • agent orchestration layer
  • AI Quality Readiness scoring platform
  • agent contribution ecosystem
  • instrument, evaluate, and iterate on agent performance
  • integrate agents with internal developer infrastructure