AI Engineer - Agentic & Autonomous Operations (m/f/x)

**xHeron is building the Service-as-Software company for short-term rental operators.** We take responsibility for guest communication, team coordination and issue resolution, so customers can hand over the work without handing over their business.

Today, we deliver that service through people, software and AI. We’re turning the expertise behind it into autonomous systems that understand situations, take action and follow through. **Not another tool to supervise. A service that gets the job done.**

We’re looking for an **AI Engineer** to build the agentic capabilities at the heart of xHeron. You’ll help shape how our agents reason, act and learn, and build a company where AI doesn’t just support the work, but increasingly delivers it.

## Tasks

**What You'll Own**

• Agent behavior & reasoning: Build and improve multi-step agent behavior, including reasoning, tool use, and human handoffs.
• Context & retrieval: Develop context and retrieval strategies that connect agents to relevant operational knowledge and reusable expertise.
• Evaluation & testing: Build evaluations and regression tests to measure decision quality, task completion, and failure patterns.
• Continuous improvement: Use production traces and operator feedback to improve models, prompts, and agent architecture.
• Production ownership: Ship and maintain production code alongside our CTO and engineering team, working closely with systems engineering on safe execution.

## Requirements

**What Makes You a Great Fit**

• **You have strong software engineering foundations and can build reliable production software in Python.**
• **You have built a substantial LLM, automation, or decision system—not only experimented through chat interfaces. Direct agent experience is valuable, but strong adjacent experience also counts.**
• **You can connect intelligence to real work:** selecting relevant context, making a bounded decision, using tools or APIs, and determining whether the intended effect actually occurred.
• **You think carefully about when AI should act, wait, ask for help, or escalate.** You understand that uncertainty, permissions, and failure handling are part of the product.
• **You have shipped software that people use and have worked through testing, debugging, operational failures, and imperfect real-world data.**
• **You assess AI behavior systematically** using representative test cases, traces, comparisons, production feedback, and clear definitions of success.
• **You investigate ambiguous problems independently, explain trade-offs clearly, and turn decisions into working software.**
• **You bring useful expertise and an independent perspective.** We value people who can transfer what they have learned from other domains and develop practical solutions to unfamiliar problems.

Around **2+ years of software engineering experience** is a useful guide, not a hard requirement. What matters is the depth of what you have built, the decisions you owned, and your ability to learn.

**Nice to have:** TypeScript/Node.js, backend integrations and tool APIs, LLM evaluations and observability, retrieval or memory systems, authorization and safety controls, or experience with an agent framework. We do not expect you to know every tool, have an AI research background, or have already built our exact system.

**You May Not Be a Great Fit If**

• **Your experience is limited to prompting, chat demos, or connecting an LLM API without owning the surrounding software.**
• **You prefer receiving a fully scoped specification rather than investigating an unclear problem and helping define the right solution.**
• **You are comfortable treating a plausible model response as success without checking whether the resulting action was correct and effective.**
• **You are not interested in owning evaluation, failure analysis, and production learning alongside feature development.**
• **You prefer narrowly bounded implementation work with stable requirements and limited responsibility for product or operational outcomes.**

## Benefits

Real ownership: you're not maintaining someone else's codebase, you're building a core, novel part of the product from the ground up.

• **Build at the core.** Own a defining part of xHeron’s technology, from the first architectural decisions to production.
• **Shape the direction.** Work directly with our CTO, challenge assumptions and help decide what we build, not just how.
• **Grow beyond the job description.** We invest in your development, with room to expand your ownership and take on technical leadership as xHeron grows.
• **Share in the upside.** Salary plus VSOP participation, so you can benefit from the value you help create.

**Our Process**

• Intro call (30 min): a conversation with Friedrich (CTO) about your background, what you've built, and why this role.
• Technical take-home case study: a short, real engineering problem, close to what you'd actually be building.
• Case study interview (1 hour): you walk us through your thinking, not just the final code.
• Culture fit (30 min): meet both Founders and make sure it's a fit both ways.