GT was founded in 2019 by a former Apple, Nest, and Google executive. GT’s mission is to connect the world’s best talent with product careers offered by high-growth companies in the UK, USA, Canada, Germany, and the Netherlands.
About the role
On behalf of our client, GT is looking for a Senior Applied Data Scientist interested in developing and testing new ML, embedding, and LLM-based approaches to solve complex data matching problems at scale.
About the Client
Our client is a leading global management consultancy known for tackling some of the world’s most complex business challenges. With a focus on strategy, transformation, and performance improvement, the firm partners with major organizations across industries to drive lasting impact.
About the Role
We are looking for a Senior Applied Data Scientist to improve how entity resolution is performed at scale.
You will develop and test new ML, embedding, and LLM-based approaches for matching complex business records across multiple data sources.
The work is centered on model quality, experimentation, and evaluation; engineering partners will help productionize successful approaches.
A key part of the role is exploring how newer foundation-model techniques can improve matching quality while remaining practical and scalable for very large datasets.
Responsibilities:
Develop better ways to match company records
•
Build new ML, embedding, and LLM-based approaches for matching entities
•
Improve how the system handles messy data, including name variations, aliases, domains, websites, firmographic attributes, multilingual records, and data hierarchies.
•
Develop scoring and ranking approaches to distinguish accurate matches from duplicates, similar-looking records, and unrelated entities.
•
Evaluate and implement AI and machine learning techniques to improve matching quality while considering accuracy, scalability, and cost.
•
Design approaches that can operate efficiently at scale, taking model usage and computational cost into consideration.
Improve evaluation, experimentation, and match quality
•
Define and improve methods for evaluating match quality, including precision, recall, false positives, false negatives, confidence, coverage, and manual review effort.
•
Assist in building trusted benchmark sets that allow us to compare new models against the current matching engine before production rollout.
•
Explore LLM-assisted review and validation to assess matching performance and benchmark more scalable approaches.
•
Turn ambiguous matching problems into clear hypotheses, experiments, metrics, and recommendations.
Partner with engineering to bring successful ideas into production
•
Work closely with data engineering and software engineering teams to turn promising prototypes into production-ready matching logic.
•
Provide engineering partners with clear model specifications, evaluation results, expected behavior, edge cases, and rollout requirements.
•
Help determine the most appropriate matching techniques based on data characteristics, confidence levels, and cost considerations.
•
Continuously evaluate matching performance, investigate regressions, and recommend improvements to models and matching logic.
•
Clearly communicate technical tradeoffs related to matching performance, scalability, cost, latency, explainability, and operational considerations.
Essential knowledge, skills & experience:
•
5–8 years of relevant experience in Data Science, Applied Data Science, Applied Machine Learning, or a similar role.
•
Strong applied ML fundamentals, with hands-on experience building and evaluating models on real data.
•
Excellent Python and SQL skills.
•
Practical experience with embeddings, semantic similarity, LLMs, or related AI techniques.
•
Hands-on experience training supervised and unsupervised models, including classification and NLP tasks.
•
Working knowledge of neural network and transformer architectures.
•
Proficiency with common ML frameworks such as TensorFlow, PyTorch, and PyCaret.
•
Experience retraining a taxonomy classifier or maintaining classification models in production.
•
Experimental judgment: able to define baselines, metrics, test sets, and error analysis that show whether quality improved.
•
Ability to explain model behavior, tradeoffs, and edge cases clearly to engineering and business partners.
Nice-to-have:
•
Experience with entity resolution, record linkage, deduplication, or similar matching problems.
•
Experience with ranking, similarity scoring, retrieval, clustering, or candidate generation.
•
Experience applying LLMs or embeddings to business problems where cost and scale matter.
•
Exposure to large-scale data platforms such as Spark, Snowflake, Databricks, or BigQuery.
•
Familiarity with company, domain, website, firmographic, or other business-entity data.