Data Scientist (Machine Learning & LLMs)

About the role

Applaudo is looking for an experienced Data Scientist to lead the design, development, and evaluation of advanced machine‑learning solutions for entity matching and deduplication. You will work with large, noisy datasets and leverage embeddings, semantic similarity, and large language models to deliver scalable, cost‑effective products.

Key responsibilities

• Build and evaluate ML models for company/entity matching, including embedding‑based and LLM‑based approaches.
• Develop scoring and ranking methodologies to differentiate true matches from duplicates, look‑alikes, and unrelated entities.
• Handle messy data sources such as names, aliases, domains, websites, firmographic attributes, and multilingual records.
• Define benchmark datasets, metrics, baselines, and error‑analysis processes.
• Design and execute experiments to validate hypotheses and compare LLM‑assisted solutions with lower‑cost alternatives.
• Analyze model behavior, edge cases, and trade‑offs while considering inference economics and scalability.
• Communicate findings and recommendations to engineering and business stakeholders.
• Establish experimental pipelines, research approaches, and thorough documentation of both successful and unsuccessful experiments.

Required profile

• 5+ years of professional experience in Data Science or Machine Learning.
• Strong applied ML fundamentals and a track record of delivering production‑ready models.
• Excellent Python and SQL programming skills.
• Hands‑on experience with embeddings, semantic similarity, LLMs, NLP, and both supervised and unsupervised learning.
• Practical knowledge of neural networks, transformer architectures, and model maintenance in production.
• Ability to design experiments, define baselines, metrics, test sets, and conduct rigorous error analysis.
• Clear communication of technical results to both engineering and business audiences.

Required skills

• Python
• SQL
• TensorFlow
• PyTorch
• PyCaret
• Embeddings
• Semantic similarity
• Large Language Models (LLMs)
• Natural Language Processing (NLP)
• Classification
• Supervised learning
• Unsupervised learning
• Neural networks
• Transformer architectures
• Spark
• Snowflake
• Databricks
• BigQuery