Senior Software Engineer, Agentforce Engines & Experiences

Salesforce Salesforce · Enterprise · San Francisco, CA

Senior Software Engineer role focused on building the core backend infrastructure and platform capabilities for Agentforce, Salesforce's AI-native future. The role involves designing, building, and operating high-performance systems for AI agents, including orchestration, reasoning pipelines, and tool invocation, on cloud infrastructure.

What you'd actually do

  1. Technical & Engineering Leadership: Champion and enforce best-in-class engineering practices across architecture reviews, code quality, scalability design, and security standards for AI platform services.
  2. AI Infrastructure: Design, build, and operate high-performance backend systems that serve as the execution layer for Agentforce — including agent orchestration, reasoning pipelines, tool invocation, and memory services.
  3. Architecture & Strategy: Collaborate with engineering leadership and architects to define and evolve the long-term technical roadmap for Agentforce engines and experiences.
  4. Emerging AI Technology: Spearhead research, prototyping, and integration of AI/ML technologies and agentic frameworks to enhance product capabilities, performance, and developer experience.
  5. Cross-Functional Collaboration: Partner closely with Product Management, Applied AI Research, and Platform teams to translate business requirements into scalable, production-grade systems.

Skills

Required

  • BS or higher in Computer Science or a related technical field
  • 5+ years of professional software engineering experience
  • Deep proficiency in Java and/or Python
  • production experience building and operating high-throughput services at scale
  • Proven experience designing, building, and maintaining production services on AWS or equivalent cloud platforms (GCP, Azure)
  • Strong knowledge of distributed systems concepts
  • Experience designing and maintaining RESTful and/or gRPC APIs
  • Excellent written and verbal communication skills
  • A passion for teaching, mentoring, and building high-performing engineering teams

Nice to have

  • Hands-on experience building or integrating LLM-based systems, agentic frameworks, or AI orchestration pipelines in production environments
  • Familiarity with AI/ML model serving infrastructure, vector stores, embeddings, or retrieval-augmented generation (RAG) patterns
  • Experience with Kubernetes, container orchestration, and cloud-native infrastructure
  • Strong background in observability
  • Experience with multi-tenant SaaS platforms and enforcing security, compliance, and data isolation at scale
  • Prior work on developer-facing platforms or internal APIs used by other engineering teams

What the JD emphasized

  • large-scale, distributed, or AI/ML-intensive backend systems
  • production experience building and operating high-throughput services at scale
  • production services on AWS or equivalent cloud platforms
  • distributed systems concepts: consistency, fault tolerance, service mesh, observability, and performance tuning
  • RESTful and/or gRPC APIs for mission-critical, latency-sensitive workflows
  • Hands-on experience building or integrating LLM-based systems, agentic frameworks, or AI orchestration pipelines in production environments
  • AI/ML model serving infrastructure, vector stores, embeddings, or retrieval-augmented generation (RAG) patterns
  • multi-tenant SaaS platforms and enforcing security, compliance, and data isolation at scale

Other signals

  • building core backend infrastructure for AI agents
  • designing and operating high-performance backend systems for agent orchestration
  • integrating AI/ML technologies and agentic frameworks