Senior Applied Data Scientist: Entity Resolution at Scale

GT; Warszawa; On-site; PLN 180,000 - 260,000; Full time

Job summary

GT is seeking a Senior Applied Data Scientist to advance entity matching at scale. You will develop and test ML, embeddings, and LLM-based approaches for matching complex business records across multiple data sources.

The role emphasizes model quality, experimentation, and evaluation, with engineering partners helping productionize successful ideas. You'll explore foundation-model techniques to improve matching while keeping costs and latency in check, working closely with data and software

Qualifications

• 5–8 years of relevant experience in Data Science or Applied Machine Learning.
• Strong Python and SQL skills.
• Experience with embeddings, semantic similarity, LLMs.
• Hands-on training of supervised and unsupervised models.
• Knowledge of neural networks and transformer architectures.
• Proficiency with ML frameworks such as TensorFlow, PyTorch, PyCaret.
• Experience retraining a taxonomy classifier in production.
• Experimental judgment with baselines, metrics, and error analysis.
• Ability to explain model behavior to engineering and business partners.

Responsibilities

• Develop ML, embedding, and LLM-based approaches to matching entities.
• Improve handling of messy data, including multilingual records.
• Develop scoring and ranking to distinguish matches from duplicates.
• Evaluate AI techniques balancing accuracy, scalability and cost.
• Design scalable approaches considering model usage and compute cost.
• Collaborate with data and software engineering to productionize models.
• Define evaluation methods for match quality and benchmarks.
• Build trusted benchmark sets for model comparison.
• Explore LLM-assisted review for scalable benchmarking.

Skills

Applied Data Science

Python & SQL

Embeddings & LLMs

Neural networks & transformers

ML frameworks (TensorFlow, PyTorch, Py

Experimentation & evaluation

Engineer collaboration

Tools

TensorFlow

PyTorch

PyCaret

Job description

GT is seeking a Senior Applied Data Scientist to advance entity matching at scale. You will develop and test ML, embeddings, and LLM-based approaches for matching complex business records across multiple data sources.

The role emphasizes model quality, experimentation, and evaluation, with engineering partners helping productionize successful ideas. You'll explore foundation-model techniques to improve matching while keeping costs and latency in check, working closely with data and software