Senior Applied Data Scientist: LLMs, NLP & Entity Matching

Applaudo; Argentina; On-site; ARS 350,000 - 700,000; Full time

Job summary

Applaudo in Argentina is seeking an experienced Data Scientist with strong applied ML expertise to build and evaluate models on large, messy data.

You will work with embeddings, semantic similarity, LLMs, NLP, and both supervised and unsupervised learning, delivering measurable improvements while balancing cost and scalability.

You will design experiments, document results, and communicate trade-offs to engineering and business teams.

Qualifications

• 5+ years professional Data Science / ML experience.
• Strong applied ML fundamentals.
• Excellent Python and SQL skills.
• Hands-on experience with embeddings and semantic similarity.
• Practical experience applying LLMs to real-world problems.
• Experience with supervised and unsupervised learning.
• Strong experience with classification and NLP.
• Knowledge of neural networks and transformer architectures.
• Hands-on experience with ML frameworks (TensorFlow, PyTorch, PyCaret).
• Experience retraining or maintaining classification models in production.
• Strong experimental design and model evaluation skills.
• Ability to evaluate model quality and show measurable improvements.
• Understanding of scalability and ML inference costs.

Responsibilities

• Build and evaluate ML approaches for company/entity matching.
• Develop embedding and LLM-based matching approaches.
• Develop scoring/ranking to identify true matches vs duplicates/lookalikes.
• Work with messy data including multilingual records and firmographic attributes.
• Define benchmarks, metrics, baselines, and error-analysis processes.
• Design and execute experiments to validate hypotheses.
• Compare LLM-assisted approaches against lower-cost alternatives.
• Analyze model behavior, edge cases, and trade-offs.
• Consider inference economics and scalability from the start.
• Communicate findings and recommendations to engineers and business stakeholders.
• Establish autonomous experimental pipelines and research approaches.
• Document successful and unsuccessful experiments.

Skills

Python

SQL

Embeddings

Semantic similarity

LLMs

NLP

Neural networks

Transformer architectures

TensorFlow

PyTorch

PyCaret

Model evaluation

Experiment design

Tools

Spark

Snowflake

Databricks

BigQuery

Job description

Applaudo in Argentina is seeking an experienced Data Scientist with strong applied ML expertise to build and evaluate models on large, messy data.

You will work with embeddings, semantic similarity, LLMs, NLP, and both supervised and unsupervised learning, delivering measurable improvements while balancing cost and scalability.

You will design experiments, document results, and communicate trade-offs to engineering and business teams.