> Markdown version of [/jobs/ext/4628366-ai-engineer](https://www.wearedevelopers.com/jobs/ext/4628366-ai-engineer). 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).

---

# AI Engineer

- **Company:** HockeyStack, Inc.
- **Location:** San Francisco, CA, United States
- **Contract:** Permanent contract
- **Skills:** JavaScript (Programming Language), Artificial Intelligence, Node.Js, TypeScript, Large Language Models, Multi-Agent Systems, Backend, Agentic-AI
- **Published:** November 7, 2026
- **Apply:** https://www.juju.com/job/28_25197_387e617cb2d8b3800a63d6f2a764fbff

## About the Role

* Ownership-first mindset - you take initiative, move fast, and figure things out
 * Thrive in early-stage, high-urgency environments where speed and impact matter
 * Fully committed to working in-person 5 days/week at our SF HQ
 * Curious, self-aware, and feedback-driven - you bring energy, not ego
 * See this role as a defining chapter - not a stepping stone or side quest

What you bring:

 * Hands-on experience building and deploying LLM-powered applications or agentic AI systems in production
 * Strong backend engineering experience with Node.js and modern JavaScript/TypeScript
 * Experience designing and orchestrating multi-agent systems, including managing agent state, memory, and context across complex workflows
 * Familiarity with modern AI frameworks and providers (Braintrust, Cerebras, Langchain or similar)
 * Understanding of multi-model architectures - knowing when and how to route tasks across different LLMs for cost, speed, and quality tradeoffs
 * A track record of shipping in fast-moving, production environments

## Description

We integrate with every tool across the go-to-market stack, combine it with first and third-party data, and build the most complete event-level data foundation in the industry. On top of it, we:

 * Mine every won and lost deal to reverse-engineer the patterns that drive revenue, then deploy agents that guide reps through the optimal process deal by deal, in real time.
 * Surface what's really driving pipeline and what isn't, replacing weeks of manual analysis with answers on demand.
 * Learn from every outcome and every rep interaction, getting sharper over time - not just when someone rewrites a prompt.

We're not wrapping LLMs around prompts and guessing. We've built a structured reasoning layer that makes agent execution deterministic and self-improving - something no other player in the market has done.

Y Combinator alum. $26M Series A led by Bessemer Venture Partners. 3× YoY growth. 8-figure ARR. 60+ TB of GTM data processed. We move fast and hire people who are ready to win. This role is based at our San Francisco HQ., * Own and continuously improve the backend systems that power all agentic AI features across the platform

 * Design, write, and maintain agents responsible for different tasks across a GTM team's workflows, leveraging the latest agent frameworks
 * Develop and maintain backend services in Node.js that power these agents
 * Build state-of-the-art context management pipelines and manage thousands of stateful agents.
 * Ship fast and often - deploying to production frequently while maintaining high-quality standards