The Machine Learning Engineer will optimize a data extraction pipeline, fine-tune text classification models, and enhance training datasets for lease processing using various NLP tools.
We are seeking a highly skilled Machine Learning Engineer to enhance and optimize our data extraction pipeline for commercial real estate lease processing. This role focuses on fine-tuning text classification models, improving training datasets, and working with large volumes of unstructured text data. The ideal candidate has experience with natural language processing (NLP), model retraining workflows, and cloud-based ML deployment.
Responsibilities:
- Improve and maintain the data extraction pipeline used for lease document processing.
- Fine-tune and retrain existing ML models for text categorization (currently using TF-IDF and Scikit-learn).
- Own the QA process for ML outputs and continuously optimize model performance.
- Enhance training datasets to improve model generalization and accuracy.
- Collaborate with the team to ensure consistent extraction of 15–30 provisions per lease document.
- Work with OCR and NLP tools to refine document parsing and classification.
- Proven experience in machine learning, with a focus on text classification and document processing.
- Strong proficiency in Python and core NLP libraries (e.g., spaCy, NLTK, scikit-learn, transformers).
- Experience with TF-IDF vectorization and traditional ML techniques for text classification.
- Familiarity with OCR technologies and PDF parsing tools (e.g., Marker).
- Experience deploying models on AWS and working with APIs like OpenAI (via Azure) and Claude (via Bedrock).
- Excellent problem-solving skills, attention to detail, and ability to work independently.
- English proficiency at the B2-C1 level
Stack:
- Python (primary language)
- AWS (cloud infrastructure)
- Scikit-learn (ML models)
- OpenAI (Azure API integration)
- Claude (via AWS Bedrock)
- OCR tools (e.g., Marker)
- Standard NLP/text processing libraries
At Devsu, we believe in creating an environment where you can thrive both personally and professionally. By joining our team, you’ll enjoy:
- A stable, long-term contract with opportunities for career growth
- A remote-friendly culture that promotes work-life balance
- Continuous training, mentorship, and learning programs to keep you at the forefront of the industry
- Free access to AI training resources and state-of-the-art AI tools to elevate your daily work
- A flexible Paid Time Off (PTO) policy as well as paid holiday days
- Challenging, world-class software projects for clients in the US and LatAm
- Collaboration with some of the most talented software engineers in Latin America and the US, in a diverse work environment
Join Devsu and discover a workplace that values your growth, supports your well-being, and empowers you to make a global impact.
Top Skills
AWS
Claude
Ocr Tools
Openai
Python
Scikit-Learn
Similar Jobs
Other
Seeking an experienced Data/ML Engineer to design and maintain data pipelines, optimize data workflows, and support AI-driven applications.
Top Skills:
SparkAWSAzure Machine LearningDatastax AstradbHadoopKafkaLangchainLlamaindexPlsqlPythonRedshiftSnowflakeSQL
Other
The Senior Data/ML Engineer will design and maintain data pipelines, manage ML workflows, optimize data storage, and collaborate with data stakeholders for BI initiatives.
Top Skills:
SparkAWSAzure Machine LearningDatastax AstradbHadoopHugging FaceKafkaLangchainLlamaindexPlsqlPythonRedshiftSnowflakeSQL
Information Technology • Security
The Regional Sales Manager will promote Axis Communications products, maintain customer relations, conduct demonstrations, and participate in sales activities for the Central America region.
Top Skills:
MS Office
What you need to know about the Sydney Tech Scene
From opera to comedy shows, the Sydney Opera House hosts more than 1,600 performances a year, yet its entertainment sector isn't the only one taking center stage. The city's tech sector has earned a reputation as one of the fastest-growing in the region. More specifically, its IT sector stands out as the country's third-largest, growing at twice the rate of overall employment in the past decade as businesses continue to digitize their operations to stay competitive.
