AI Engineer (LLMs + Knowledge Graphs) (m/f/d)

<p>Pinnipedia is a new Berlin startup building a cloud platform that automates and assists the creation of <strong>audit-ready IT-security concepts</strong> (e.g., BSI-Grundschutz, C5). We’re IGP-funded (2025/26) and co-develop with FU Berlin and pilot users from industry and security consulting.</p>
<p>We’re hiring an <strong>AI Engineer</strong> to turn messy inputs into structured knowledge and reliable answers. You’ll design and operate <strong>knowledge-graph + LLM (RAG)</strong> pipelines, model/ingest domain ontologies, and own evaluation so we can ship trustworthy features.</p>
<h2>Tasks</h2>
<p><strong>Knowledge graphs &#x26; data</strong></p>
<ul>
<li>Model the domain (ontology/taxonomy); build ETL into a graph store.</li>
<li>Author queries (SPARQL/Cypher) and surface graph facts and relationships in features.</li>
</ul>
<p><strong>RAG &#x26; LLM integration</strong></p>
<ul>
<li>Design retrieval and answer generation workflows (indexing, chunking, reranking).</li>
<li>Orchestrate prompts/tools; balance KG, vector search, and business rules.</li>
</ul>
<p><strong>Evaluation &#x26; quality</strong></p>
<ul>
<li>Define and track retrieval/answer metrics (e.g., precision/recall, faithfulness).</li>
<li>Build test fixtures and regression checks; monitor drift and data quality.</li>
</ul>
<p><strong>Production &#x26; collaboration</strong></p>
<ul>
<li>Ship well-tested Python components (FastAPI jobs/services); document decisions; work from a clear backlog with PO and engineers.</li>
</ul>
<h2>Requirements</h2>
<p><strong>Must-have</strong></p>
<ul>
<li>Strong <strong>Python</strong> and data engineering fundamentals.</li>
<li>Hands-on with <strong>knowledge graphs</strong> (ontology design + queries) and a graph DB.</li>
<li>Practical <strong>RAG</strong> experience (indexing, retrieval, evaluation).</li>
<li>Testing mindset (pytest), version control, and clear documentation.</li>
<li><strong>English required</strong> (German nice-to-have).</li>
</ul>
<p><strong>Nice-to-have</strong></p>
<ul>
<li>Security/compliance awareness; prompt/agent tooling; spaCy/Transformers.</li>
<li>Observability for ML/LLM systems; simple dashboards for quality metrics.</li>
<li>Cloud basics (AWS/Azure), containers (Docker); CI/CD.</li>
</ul>
<h2>Benefits</h2>
<p><strong>Hybrid, full-time</strong> with flexible scheduling; occasional on-site days in Berlin.</p>
<p><strong>Competitive salary:</strong> <strong>60.000–85.000 €</strong> base (more for exceptional senior profiles).</p>
<p>Small, focused team; direct collaboration with the Product Owner and Full-Stack Engineer.</p>
<p>Modern tooling, real ownership, and a learning budget for role-relevant training.</p>
<p>Impact: help SMEs meet rising security requirements with less friction.</p>
<p><strong>Apply on JOIN</strong> with your CV (PDF) and a short note (max <strong>200 words</strong>) describing <strong>how you would design a KG-backed RAG pipeline</strong> (ontology scope, indexing, retrieval, and evaluation you’d use).<br>
<strong>Process:</strong> 20-min intro → 90-min practical (graph modeling + retrieval evaluation) → 45-min team chat → references. We review applications within <strong>5 business days</strong>.</p>
<p>Find more <a href="https://www.arbeitnow.com/english-speaking-jobs">English Speaking Jobs in Germany</a> on Arbeitnow</a>