Job
- Level
- Experienced
- Job Field
- Software, Data
- Employment Type
- Full Time
- Contract Type
- Permanent employment
- Location
- Berlin
- Working Model
- Hybrid, Onsite
Job Summary
In this role, you design memory systems for AI agents, enhancing their abilities through retrieval and ranking improvements. You will analyze data and experiment with modern approaches such as semantic search and trajectory analysis.
Job Technologies
Your role in the team
- 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.
- Untersuchen Sie Fehler mithilfe von Traces, Datensätzen und Produktionsfeedback.
- Experimentieren Sie mit Ansätzen wie semantischer Suche, graphbasierter Abfrage, Reranking, Trajektorienanalyse und selektiver Wiedergabe.
- 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.
This text has been machine translated. Show original
Our expectations of you
Qualifications
- 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.
- Klare schriftliche und mündliche Kommunikation in Englisch.
Experience
- Starke Software-Engineering-Fähigkeiten und Erfahrung im Aufbau von Produktionssystemen.
- Practical experience working with LLMs, agents, retrieval systems, or applied machine learning.
This text has been machine translated. Show original
What we offer
- 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.
This text has been machine translated. Show original
Benefits
Work-Life-Integration
Topics You Will Work On
Job Locations
About Your Employer
GlassFlow
GlassFlow GmbH is a Berlin-based startup focused on creating data infrastructures for AI agents. With its two main products, Tares and Rius, the company provides solutions for contextual data feeds as well as tracing and debugging in production. GlassFlow targets companies looking to efficiently utilize agents in production.
Description
- Company Type
- Startup
- Working Model
- Hybrid, Onsite
- Industry
- Internet, IT, Telecommunication
AI Engineer
- Location
- Berlin
- Working Model
- Hybrid, Onsite
- Diversity
- Open for all genders
- English Only
- English only required
