AI Engineer

<p><strong>About GlassFlow:</strong></p> <p>GlassFlow is the data infrastructure for AI agents in production. It has two products: GlassFlow Tares, which feeds agents correlated data from every system they touch, and GlassFlow Rius, which traces and debugs what agents do once they're running.</p> <p>We’re a Berlin startup with a Silicon Valley mentality, backed with $5.9m from Upfront Ventures, the CEO of GitHub, the ex-CTO of Aiven, and more world-class investors.</p> <p>The founders are serial entrepreneurs with more +10y of experience in building and selling data products.</p> <h2>Tasks</h2> <p><strong>Why is this role special</strong></p> <ul> <li>Design and build memory systems for AI agents.</li> <li>Improve retrieval, ranking, context assembly, and long-term memory.</li> <li>Develop systems for entity resolution, temporal reasoning, provenance, and knowledge representation.</li> <li>Build agent capabilities that combine reasoning with reliable tool use.</li> <li>Design evaluations for retrieval quality, agent behavior, and end-to-end task performance.</li> <li>Investigate failures using traces, datasets, and production feedback.</li> <li>Experiment with approaches such as semantic search, graph-based retrieval, reranking, trajectory analysis, and selective replay.</li> <li>Ensure agents retrieve and use information according to user permissions and organizational access controls.</li> <li>Improve the reliability, latency, and cost of AI systems in production.</li> <li>Collaborate directly with the founders and broader engineering team on product direction and architecture.</li> </ul> <h2>Requirements</h2> <p><strong>What we’re looking for</strong></p> <p><strong>You are:</strong></p> <ul> <li>Strong software-engineering skills and experience building production systems.</li> <li>Practical experience working with LLMs, agents, retrieval systems, or applied machine learning.</li> <li>Proficiency in Python and familiarity with modern backend and data infrastructure.</li> <li>A solid understanding of embeddings, vector search, retrieval-augmented generation, evaluation, and prompting.</li> <li>An experimental mindset: you form hypotheses, build prototypes, measure results, and iterate quickly.</li> <li>The ability to navigate ambiguous problems and turn research ideas into reliable product capabilities.</li> <li>Strong product judgment and an interest in how people actually use AI systems.</li> <li>Clear written and verbal communication in English.</li> </ul> <h2>Benefits</h2> <p><strong>What you’ll get</strong></p> <ul> <li>Real ownership: competitive equity (everyone at GlassFlow is an owner).</li> <li>The chance to build something that changes how the world streams data.</li> <li>The opportunity to build for global tech brands from day one.</li> <li>A career trajectory that will 10x your skills and network.</li> </ul> <p><strong>Benefits:</strong></p> <ul> <li>Competitive salary with Stock Option Grant</li> <li>Ticket for public transportation in Berlin</li> <li>Company credit card with a monthly allowance</li> <li>Newest tech of your choosing</li> <li>Annual Learning budget for personal development</li> <li>Generous WFH policy and a budget for home office setup</li> </ul> <p>GlassFlow is an equal opportunity employer that values diversity in the workplace. We encourage applications from all qualified individuals, including those with diverse backgrounds and disabilities.</p> <p>Find more <a href="https://www.arbeitnow.com/english-speaking-jobs">English Speaking Jobs in Germany</a> on Arbeitnow</a>