About this job
<p><strong>xHeron is building the Service-as-Software company for short-term rental operators.</strong> We take responsibility for guest communication, team coordination and issue resolution, so customers can hand over the work without handing over their business.</p>
<p>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. <strong>Not another tool to supervise. A service that gets the job done.</strong></p>
<p>We’re looking for an <strong>AI Engineer</strong> 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.</p>
<h2>Tasks</h2>
<p>We are looking for an AI Harness Engineer to build the software layer that turns language models into dependable operational systems.</p>
<p>You will work on orchestration, context assembly, tool execution, state, permissions, evaluations, observability, failure recovery, and human handoffs. The goal is not merely to generate a good response.</p>
<p><strong>What You’ll Own</strong></p>
<ul>
<li><strong>Agent harness architecture:</strong> Build the control layer around models: task decomposition, state management, model and tool selection, execution loops, checkpoints, retries, stopping conditions, and human handoffs.</li>
<li><strong>Decision and execution behavior:</strong> Design how agents interpret situations, choose actions, manage uncertainty, and complete bounded operational tasks—not only how they generate text.</li>
<li><strong>Context and memory:</strong> Determine what an agent needs to know at each step. Build context assembly, retrieval, memory, evidence selection, and knowledge-maintenance strategies while managing relevance, latency, and cost.</li>
<li><strong>Tools and real-world effects:</strong> Connect agents to APIs and operational systems through explicit tool contracts, permissions, validation, idempotency, and confirmation that the intended effect actually occurred.</li>
<li><strong>Evaluation and regression testing:</strong> Build representative evaluation suites and automated tests for decision quality, tool use, task completion, safety, escalation behavior, and recurring failure patterns.</li>
<li><strong>Observability and failure analysis:</strong> Make agent behavior inspectable through structured traces, state, outcomes, and error classification. Diagnose failures across models, prompts, context, tools, and surrounding software.</li>
<li><strong>Continuous improvement:</strong> Use evaluations, production traces, operator feedback, and controlled experiments to improve prompts, context, tools, model choices, and agent architecture.</li>
<li><strong>Production ownership:</strong> Ship and operate production Python software alongside our CTO and engineering team. Work closely with systems engineering on integrations, authorization, durable state, recovery, and safe execution.</li>
</ul>
<h2>Requirements</h2>
<p><strong>What Makes You a Great Fit</strong></p>
<ul>
<li><strong>You are a strong software engineer who can design, build, test, and operate reliable production systems in Python.</strong></li>
<li><strong>You have built a substantial LLM-powered, automation, workflow, or decision system: not only notebooks, chat interfaces, prompt experiments, or a basic retrieval pipeline.</strong></li>
<li><strong>You understand the engineering layer around a model:</strong> orchestration, state, context, tools, structured outputs, permissions, retries, fallbacks, observability, and evaluations.</li>
<li><strong>You can connect intelligence to real work:</strong> selecting relevant evidence, making a bounded decision, invoking tools or APIs, and verifying that the intended result occurred.</li>
<li><strong>You design for partial failure and uncertainty.</strong> You think deliberately about when an agent should act, retry, wait, stop, ask for help, or escalate.</li>
<li><strong>You evaluate behavior systematically.</strong> You use representative cases, traces, outcome checks, comparisons, and regression tests rather than treating a plausible response as proof of success.</li>
<li><strong>You have shipped software that people or operational processes depend on</strong> and have worked through debugging, timeouts, inconsistent data, changing APIs, and production incidents.</li>
<li><strong>You can investigate ambiguous problems independently, define a useful system boundary, explain trade-offs clearly, and turn decisions into working software.</strong></li>
<li><strong>You care about simplicity and control.</strong> You know when a deterministic workflow is better than an agent and when additional autonomy is justified by evidence.</li>
<li><strong>You bring useful expertise and an independent perspective.</strong> Strong adjacent experience in workflow engines, developer tooling, distributed systems, automation platforms, or integration-heavy backend software can be highly relevant when paired with credible LLM-system understanding.</li>
</ul>
<p>Around 2+ years of professional software-engineering experience is a useful guide, not a hard requirement. What matters is the technical depth of what you built, the decisions and production outcomes you owned, and your ability to learn unfamiliar systems.</p>
<p><strong>You May Not Be a Great Fit If</strong></p>
<ul>
<li><strong>Your LLM experience is mainly prompt engineering, chatbots, basic RAG, or connecting a model API to a user interface.</strong></li>
<li><strong>Your background is primarily offline data analysis, model training, or experimentation, and you do not want to own production software and operational behavior.</strong></li>
<li><strong>You treat retrieval as the complete agent architecture rather than one possible source of context within a larger execution system.</strong></li>
<li><strong>You consider a coherent model response successful without verifying the decision, tool call, state change, or real-world outcome.</strong></li>
<li><strong>You rely on an agent framework to provide the system design and are not comfortable reasoning about the control flow, state, permissions, and failure behavior underneath it.</strong></li>
<li><strong>You are not interested in owning evaluations, trace analysis, regression testing, and production learning alongside feature development.</strong></li>
<li><strong>You prefer fully scoped implementation tasks with stable requirements and limited responsibility for product or operational outcomes.</strong></li>
</ul>
<h2>Benefits</h2>
<p>Real ownership: you're not maintaining someone else's codebase, you're building a core, novel part of the product from the ground up.</p>
<ul>
<li><strong>Build at the core.</strong> Own a defining part of xHeron’s technology, from the first architectural decisions to production.</li>
<li><strong>Shape the direction.</strong> Work directly with our CTO, challenge assumptions and help decide what we build, not just how.</li>
<li><strong>Grow beyond the job description.</strong> We invest in your development, with room to expand your ownership and take on technical leadership as xHeron grows.</li>
<li><strong>Share in the upside.</strong> Salary plus VSOP participation, so you can benefit from the value you help create.</li>
</ul>
<p><strong>Our Process</strong></p>
<ul>
<li>Intro call (15-30 min): a conversation with Friedrich (CTO) about your background, what you've built, and why this role.</li>
<li>Technical take-home case study: a short, real engineering problem, close to what you'd actually be building.</li>
<li>Case study interview (1 hour): you walk us through your thinking, not just the final code.</li>
<li>Culture fit (30 min): meet both Founders and make sure it's a fit both ways.</li>
</ul><p>Find more <a href="https://www.arbeitnow.com/english-speaking-jobs">English Speaking Jobs in Germany</a> on Arbeitnow</a>