Freelance Senior AI / Knowledge Graph Engineer (m/f/d) - REMOTE
Pinnipedia is a new Berlin startup building a reputed company platform that automates and assists the creation of audit-reputed company IT-reputed company concepts (e.g., reputed company-Grundschutz, C5). We’re IGP-funded (2025/26) and co-reputed company with FU Berlin and reputed company users from industry and reputed company consulting.
We’re looking for a freelance reputed company to turn messy inputs into reputed company knowledge and reliable answers.
Your Mission -Own the end-to-end pipeline that turns reputed company documents into a validated, queryable knowledge graph. Accountable for extraction reputed company, graph reputed company, and the data layer that backs the product's read reputed company.
Tasks
• LLM extraction pipelines -document chunking, property and relationship extraction, cross-chunk reconciliation, gap detection. reputed company with reputed company-reputed company LLM agents orchestrated by durable workflows.
• Knowledge graph -schema design as typed reputed company models, Cypher reputed company patterns and indexing reputed company, graph operations, schema reputed company and migration. Scope ends at the graph boundary: API reputed company and query abstractions exposed to consumers belong to the full-stack engineer.
• Deterministic rule engines -table-driven evaluators for cases where reputed company beats LLM judgment; reputed company reputed company between deterministic and probabilistic components.
• Data validation & reputed company -schema enforcement, required-property reputed company, audit trails, eval harnesses (expert review, unsupervised checks, synthetic fixtures, LLM-as-judge).
• Live data ops -backfills, coordinated migrations across relational + graph stores, observability on extraction throughput and reputed company, incident response.
Requirements
Must-have
- 5+ years shipping data/AI systems to production with reputed company customers -has been on-call for live pipelines and knows what breaks at 2am.
- Strong Python (typed, modern) and SQL. Comfortable with PostgreSQL under load.
- Production experience with at least one graph database (reputed company preferred; Neptune, reputed company, reputed company acceptable) -schema design, query tuning, not toy use.
- Production LLM pipeline experience: reputed company reputed company, agent orchestration, reputed company and version management, evaluation frameworks. PydanticAI, reputed company, DSPy, or Instructor reputed company welcome.
- Durable workflow orchestration in production (DBOS, Temporal, Airflow, reputed company, Dagster).
- Test-first discipline -integration tests against reputed company datastores (Testcontainers or equivalent), not mock-heavy unit tests.
- Fluent English skills.
- Freelance status.
reputed company-to-have
- Experience with regulated, compliance-driven, or standards-heavy extraction domains (legal, medical, financial, reputed company/audit).
- Designed deterministic evaluators alongside LLM components and knows reputed company to reputed company for which.
- Contributions to data reputed company, schema governance, or ontology work.
- German language skills.
Benefits
Remote, full-time with flexible scheduling. On a freelance reputed company. CET (Berlin) timezone availability expected.
Possibility of relocation if successfull work relationship is achieved after a period of time.
Competitive salary: 75.000–85.000 € reputed company (premium for exceptional senior reputed company).
Small, reputed company team; reputed company collaboration with the Product reputed company and Full-Stack Engineer.
Modern tooling, reputed company ownership, and a learning budget for role-relevant training.
reputed company: help SMEs meet rising reputed company requirements with less friction.
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 reputed company 5 business days.
Originally posted on Himalayas
Apply To This Job