Software Engineering Smts - Agentforce Reasoning Engine

Salesforce Salesforce · Enterprise · San Francisco, CA

Salesforce is seeking an AI Software Engineer to build and scale the Agentforce Reasoning Engine, a core Python service for multi-agent orchestration. The role involves designing and implementing scalable backend services, integrating with LLMs, managing state, and ensuring system reliability for millions of customers. Experience with production AI systems, Python, async services, distributed systems, and LLM integration is required.

What you'd actually do

  1. Build and own end-to-end scalable backend services powering multi-agent orchestration, supporting thousands of concurrent tenants at production scale — using AI as a core part of your development workflow to push the limits of what's possible.
  2. Design and orchestrate complex systems where AI agents integrate seamlessly into workflows, including stateful session management using Redis and distributed storage patterns.
  3. Drive system reliability through automation, capacity planning, performance tuning, monitoring, and root cause analysis — and participate in on-call rotations to keep production healthy.
  4. Contribute to building and maintaining shared system context — an explicit repository of system designs, constraints, and standards — that enables AI to operate accurately and reliably across thousands of tenants.

Skills

Required

  • 3+ years of industry experience building production AI systems and/or backend services
  • strong Python skills
  • hands-on experience building async services using FastAPI or equivalent
  • experience with distributed, scalable systems
  • modern data storage and messaging frameworks such as Redis, Kafka
  • container orchestration tools like Docker and Kubernetes
  • experience integrating with large language models (LLMs)
  • working with prompt engineering in production systems
  • demonstrated, genuine AI-first approach to engineering
  • advanced prompt engineering skills

Nice to have

  • experience with multi-agent orchestration or agentic AI frameworks
  • familiar with vector databases, embeddings, and retrieval systems
  • worked on conversational AI or voice-integrated services
  • track record of strong cross-team collaboration
  • clear written and verbal communication

What the JD emphasized

  • production AI systems
  • multi-agent orchestration
  • production scale
  • integrating with large language models (LLMs)
  • prompt engineering in production systems
  • AI-first approach to engineering
  • advanced prompt engineering skills

Other signals

  • building and scaling the Agentforce Reasoning Engine
  • core Python service powering multi-agent orchestration
  • production scale
  • integrating with large language models (LLMs)