> Markdown version of [/jobs/ext/4629762-staff-software-engineer-ai-agents](https://www.wearedevelopers.com/jobs/ext/4629762-staff-software-engineer-ai-agents). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Staff Software Engineer, AI Agents

- **Company:** PEOPLE INC.
- **Location:** San Francisco, CA, United States
- **Salary:** $270,000.0 - $300,000.0
- **Contract:** Permanent contract
- **Skills:** Artificial Intelligence, Systems Engineering, Distributed Systems, Python (Programming Language), Natural Language Processing, TypeScript, Management of Software Versions, Retrieval-Augmented Generation, Large Language Models, Backend, Agentic-AI
- **Published:** November 7, 2026
- **Apply:** https://www.juju.com/job/28_25304_2ffcb2389cc479e1d1d862881e336cc1

## About the Role

* Ample experience in backend or systems engineering
 * Exposure to applied AI systems (LLMs, NLP, RAG)
 * Proficiency in Python; experience with distributed systems is a plus
 * Familiarity with embeddings, vector DBs, and prompt iteration
 * Ability to move fast and own projects from idea through production
 * Bonus: experience building eval frameworks or internal ML infra
 * Python, TypeScript
 * Prompting libraries, orchestration tooling

## Description

You'll be part of a cross-functional AI task force reporting into engineering leadership, working closely with product, design, and infra. This is a hands-on, end-to-end role ideal for engineers who want to prototype, ship, and scale real features - not just build demos. You'll split your time between user-facing copilots and the backend infra that powers them.

What You'll Do

 * Build LLM-powered assistants to streamline domain expert workflows
 * Design RAG pipelines using structured and unstructured internal data
 * Develop internal ML tooling for versioning, observability, and orchestration
 * Tune prompts, build eval harnesses, and iterate based on real-world feedback
 * Contribute to platform components that enable scalable experimentation