Desarrollador De Inteligencia Artificial - Remoto

Visa Hunt; Buenos Aires; A distancia; ARS 800.000 - 1.100.000; Jornada completa

Descripción de la vacante

Visa Hunt is seeking a Machine Learning Engineer with strong Python and NLP focus to build models for document understanding in the fintech space. You will manipulate data with Pandas/NumPy and develop NLP solutions using spaCy, NLTK, and transformer-based methods.

You will also implement fuzzy matching, OCR-based extraction, and REST API deployment using Docker and Azure ML, while shaping data pipelines and ETL processes in a collaborative, cross-functional environment.

Formación

• Proficient in Python for ML model development and data analysis.
• Experience applying NLP techniques to real-world text data.
• Strong understanding of ML concepts, algorithms, and evaluation.
• Familiarity with ETL design and data pipelines.

Responsabilidades

• Develop and implement ML models for document understanding and processing.
• Use Pandas/NumPy and scikit-learn for data manipulation and modeling.
• Apply NLP with spaCy, NLTK, or transformers to extract meaning from text.
• Implement fuzzy matching (Levenshtein, record linkage) for data accuracy.
• Process documents via OCR, PDF parsing, and Excel extraction.
• Deploy ML models as REST APIs using Docker and Azure ML.
• Apply supervised and unsupervised learning techniques.
• Design and manage data pipelines and ETL processes.
• Collaborate with cross-functional teams to meet goals.

Conocimientos

Python

NLP

Data manipulation

Machine learning

ETL design

REST API development

Collaboration

Herramientas

Pandas

NumPy

scikit-learn

spaCy

NLTK

Transformers

Fuzzy matching

OCR

PDF parsing

Excel data extraction

Docker

Azure ML

Descripción del empleo

We are seeking a Machine Learning Engineer with strong expertise in Python and a focus on Natural Language Processing (NLP) to join our team. The ideal candidate will have experience in the finance or fintech domain, specifically in reconciliation and accounting.

Responsibilities:

Develop and implement machine learning models for document understanding and processing.
Utilize Python libraries such as Pandas, NumPy, and scikit-learn for data manipulation and analysis.
Apply NLP techniques using libraries like spaCy, NLTK, or transformers.
Implement fuzzy matching algorithms (., Levenshtein distance, record linkage) for data accuracy.
Process documents using OCR, PDF parsing, and Excel data extraction methods.
Deploy machine learning models as REST APIs using Docker and Azure ML.
Understand and apply supervised and unsupervised learning techniques.
Design and manage data pipelines and ETL processes.
Collaborate with cross-functional teams to meet project goals.