Software Engineering SMTS - Agentforce Reasoning Engine

Salesforce•San Francisco, CA

3d•Hybrid

About The Position

Salesforce is the #1 AI CRM, where humans with agents drive customer success together. The Agentforce Reasoning Engine team is a group of Generative AI Application Engineers building the core Python/FastAPI service that powers multi-agent orchestration at Salesforce — enabling intelligent agents to reason, plan, and act on behalf of millions of customers every day. Based in San Francisco, CA and Bellevue, WA, you'll join a collaborative team that loves to learn and teach, and you'll play a direct role in shaping the AI backbone of Agentforce.

Requirements

4+ years of experience building production AI systems and/or backend services.
Strong Python programming skills and experience building production-grade async services (FastAPI or equivalent).
Hands-on experience with distributed, scalable systems and modern data storage frameworks such as Redis, Kafka, and Docker/Kubernetes.
Experience integrating with LLMs and prompt engineering in production systems.
A related technical degree required.

Nice To Haves

Experience with multi-agent orchestration or agentic AI frameworks.
Familiarity with vector databases, embeddings, and retrieval systems.
Experience with conversational AI or voice-integrated services.
Collaborate well across teams and communicate clearly in writing and in discussion.

Responsibilities

Build and own scalable backend services powering multi-agent orchestration, supporting thousands of concurrent tenants at production scale.
Design and improve stateful session management using Redis and distributed storage patterns, ensuring reliability across LLM call chains.
Drive system performance through automation, including capacity planning, monitoring, and root cause analysis.
Collaborate with Product Managers, Application Architects, and AI researchers to bring agent reasoning capabilities from concept to production.