Tasks:
- * Build and evaluate entity-matching models
- * Compare LLM approaches with lower-cost alternatives
- * Create entity scoring and ranking methods
- * Define benchmark datasets, metrics, and baselines
- * Design experiments and analyze model errors
- * Develop embedding and LLM based matching approaches
- * Document experiments and communicate recommendations
- * Evaluate model quality, inference costs, and scalability
Perks/Benefits:
Skills/Tech stack required:
[Classification] [Deduplication] [Embeddings] [Entity Resolution] [Error Analysis] [Experimental Design] [Language Models] [Language Processing] [Large Language Models] [Machine Learning] [Model Evaluation] [Natural Language] [Natural Language Processing] [Neural Networks] [PyCaret] [Python] [PyTorch] [Ranking] [Record Linkage] [Semantic similarity] [SQL] [Supervised Learning] [TensorFlow] [Transformer Architectures] [Unsupervised Learning]
Educational requirements:
N/A
Role(s):
[Data Scientist] [Scientist]