About GlassFlow:

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.

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.

The founders are serial entrepreneurs with more +10y of experience in building and selling data products.

Tasks

Why is this role special

• Design and build memory systems for AI agents.
• Improve retrieval, ranking, context assembly, and long-term memory.
• Develop systems for entity resolution, temporal reasoning, provenance, and knowledge representation.
• Build agent capabilities that combine reasoning with reliable tool use.
• Design evaluations for retrieval quality, agent behavior, and end-to-end task performance.
• Investigate failures using traces, datasets, and production feedback.
• Experiment with approaches such as semantic search, graph-based retrieval, reranking, trajectory analysis, and selective replay.
• Ensure agents retrieve and use information according to user permissions and organizational access controls.
• Improve the reliability, latency, and cost of AI systems in production.
• Collaborate directly with the founders and broader engineering team on product direction and architecture.

Requirements

What we’re looking for

You are:

• Strong software-engineering skills and experience building production systems.
• Practical experience working with LLMs, agents, retrieval systems, or applied machine learning.
• Proficiency in Python and familiarity with modern backend and data infrastructure.
• A solid understanding of embeddings, vector search, retrieval-augmented generation, evaluation, and prompting.
• An experimental mindset: you form hypotheses, build prototypes, measure results, and iterate quickly.
• The ability to navigate ambiguous problems and turn research ideas into reliable product capabilities.
• Strong product judgment and an interest in how people actually use AI systems.
• Clear written and verbal communication in English.
• Willing to work at least once a week in our Berlin office

Benefits

What you’ll get

• Real ownership: competitive equity (everyone at GlassFlow is an owner).
• The chance to build something that changes how the world streams data.
• The opportunity to build for global tech brands from day one.
• A career trajectory that will 10x your skills and network.

Benefits:

• Competitive salary with Stock Option Grant
• Ticket for public transportation in Berlin
• Company credit card with a monthly allowance
• Newest tech of your choosing
• Annual Learning budget for personal development
• Generous WFH policy and a budget for home office setup

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.