AI Cross-Lingual Knowledge Alignment Engineer

Wavion Intelligence

Remote · $130k – $160k / year · Full-time · Posted 4 months ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

A knowledge graph built from English Wikipedia doesn't know that the French Wikipedia article on the same concept uses a different taxonomy, assigns different parent categories, or links to different related concepts. When your enterprise knowledge platform serves 40 countries and the underlying knowledge base is fragmented by language, entity alignment becomes a core product problem. We maintain a multilingual enterprise knowledge graph covering 28 languages and 180 million entity-relationship triples. The alignment layer — which ensures that the same real-world concept is represented consistently across language partitions — is currently maintained with rules and human review. You'll replace 70% of that manual work with ML-based cross-lingual alignment models. You'll design the embedding approach for cross-lingual entity matching, build the alignment confidence scoring that decides when human review is needed, and develop the feedback loop that improves alignment quality from reviewer corrections.

Fully remote.

Responsibilities

Design cross-lingual entity alignment models using multilingual embeddings
Build confidence scoring for alignment decisions and human review routing
Implement feedback loops from reviewer corrections to improve alignment quality
Evaluate alignment quality across language pairs with different graph density
Reduce manual review workload from 100% to under 30% on high-confidence alignments
Collaborate with knowledge graph engineers on schema consistency

Requirements

5+ years in NLP engineering with multilingual or knowledge graph experience
Experience with cross-lingual embeddings, entity linking, or knowledge graph alignment
Familiarity with Hugging Face multilingual models and fine-tuning
Strong Python skills and comfort with graph data structures
Understanding of knowledge representation and ontology design