AI Engineer (LLMs + Knowledge Graphs) (mfd)

Pinnipedia Technologies GmbH; Berlin; Hybrid; EUR 60.000 - 85.000; Vollzeit

Zusammenfassung

A Berlin startup seeks a Data Engineer to develop a cloud platform automating IT-security concepts. Responsibilities include modeling knowledge domains, designing retrieval workflows, and ensuring quality metrics. Must have strong Python skills and hands-on experience with knowledge graphs and graph databases. Fluency in English is required, and knowledge of German is a plus. The role offers a competitive salary of €60,000 – €85,000, alongside a hybrid work environment and professional development opportunities.

Leistungen

Flexible scheduling

Learning budget for training

Direct collaboration with the team

Qualifikationen

• Strong Python and data engineering fundamentals.
• Hands-on with knowledge graphs and a graph DB.
• Practical RAG experience including evaluation metrics.
• Testing mindset with version control and documentation.
• Fluent English required, German is a plus.

Aufgaben

• Model the domain with ontology and build ETL into a graph store.
• Design retrieval workflows and balance vector search with business rules.
• Track precision/recall metrics and monitor data quality.
• Ship well-tested Python components and document decisions.

Kenntnisse

Python

Data engineering fundamentals

Knowledge graphs

Machine Learning

Natural Language Processing

Tools

Graph Databases

SPARQL

Neo4j

Docker

AWS

Jobbeschreibung

Pinnipedia is a new Berlin startup building a cloud platform that automates and assists the creation of audit‑ready IT‑security concepts (e.g. BSI‑Grundschutz C5). We are IGP‑funded (2025 / 26) and co‑develop with FU Berlin and pilot users from industry and security consulting.

Tasks

Knowledge graphs & data (40%)

• Model the domain (ontology / taxonomy); build ETL into a graph store.
• Author queries (SPARQL / Cypher) and surface graph facts and relationships in features.

RAG & LLM integration (30%)

• Design retrieval and answer generation workflows (indexing, chunking, reranking).
• Orchestrate prompts / tools; balance KG vector search and business rules.

Evaluation & quality (20%)

• Define and track retrieval / answer metrics (e.g. precision / recall, faithfulness).
• Build test fixtures and regression checks; monitor drift and data quality.

Production & collaboration (10%)

• Ship well‑tested Python components (FastAPI jobs / services); document decisions; work from a clear backlog with PO and engineers.

Requirements

Must‑have

• Strong Python and data engineering fundamentals.
• Hands‑on with knowledge graphs (ontology design queries) and a graph DB.
• Practical RAG experience (indexing, retrieval, evaluation).
• Testing mindset (pytest), version control and clear documentation.
• English required (German nice‑to‑have).

Nice‑to‑have

• Security / compliance awareness; prompt / agent tooling; spaCy / Transformers.
• Observability for ML / LLM systems; simple dashboards for quality metrics.
• Cloud basics (AWS / Azure), containers (Docker); CI / CD.

Benefits

Hybrid full‑time with flexible scheduling; occasional on‑site days near Berlin / Brandenburg (Ketzin / Havel).

Competitive salary: 60,000 – 85,000 base (more for exceptional senior profiles).

Small focused team; direct collaboration with the Product Owner and Full‑Stack Engineer.

Modern tooling, real ownership and a learning budget for role‑relevant training.

Impact

Help SMEs meet rising security requirements with less friction.

Apply on JOIN

Apply on JOIN with your CV (PDF) and a short note (max 200 words) describing how you would design a KG‑backed RAG pipeline (ontology scope, indexing, retrieval and evaluation you’d use).

Process

20‑min intro, 90‑min practical (graph modeling, retrieval, evaluation), 45‑min team chat, references. We review applications within 5 business days.

Key Skills

Graph Databases, Data Analytics, AI, Ontology, OWL, RDF, SPARQL, Natural Language Processing, Neo4j, Knowledge Management, Taxonomy