Software Engineering SMTS - Agentforce Reasoning Engine

Salesforce•San Francisco, CA

5d•$178,900 - $246,000•Hybrid

About The Position

Salesforce is looking for an AI Software Engineer to join the team building and scaling the Agentforce Reasoning Engine — the core Python service powering multi-agent orchestration for millions of customers. You will be part of a collaborative team of Generative AI Application Engineers who are passionate about designing the reasoning backbone of Agentforce and who love to learn, teach, and grow together.

Requirements

3+ years of industry experience building production AI systems and/or backend services, with strong Python skills and hands-on experience building async services using FastAPI or equivalent.
Experience with distributed, scalable systems and modern data storage and messaging frameworks such as Redis, Kafka, and container orchestration tools like Docker and Kubernetes.
Experience integrating with large language models (LLMs) and working with prompt engineering in production systems.
A demonstrated, genuine AI-first approach to engineering — using AI tools (e.g., Claude Code, GitHub Copilot, Cursor) to move faster, build fluency across the stack, and contribute beyond your core specialty, including advanced prompt engineering skills to make AI outputs reliable, secure, and production-ready.
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, or have worked on conversational AI or voice-integrated services.
A track record of strong cross-team collaboration and clear written and verbal communication.

Responsibilities

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.
Design and orchestrate complex systems where AI agents integrate seamlessly into workflows, including stateful session management using Redis and distributed storage patterns.
Drive system reliability through automation, capacity planning, performance tuning, monitoring, and root cause analysis — and participate in on-call rotations to keep production healthy.
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.