This is a fully remote position, open to applicants in Brazil.

📋 Description

• Create predictive models and machine learning algorithms to address intricate business challenges, guiding the process from data analysis to result validation and interpretation, with an emphasis on measurable outcomes.

• Utilize Python (Scikit-learn, XGBoost, LightGBM), notebooks (Jupyter, Databricks), experimentation tools (MLflow), and statistical libraries (Statsmodels, SciPy), employing supervised, unsupervised, and deep learning techniques as required.

• Assess the performance of RAG systems by analyzing cost metrics (tokens and latency) and response quality, utilizing indicators such as semantic similarity, BLEU, and ROUGE, among others.

• Construct text-ingestion pipelines for vector databases using AWS OpenSearch, and develop APIs with LangChain and LangGraph integrated with OpenAI and AWS Bedrock.

• Collaborate with AWS cloud services (including S3, Lambda, Parameter Store, and Secrets Manager), as well as serverless architectures on AWS and Azure, containerized applications within AWS environments, and Azure Document Intelligence for document extraction and processing.

⛳️ Requirements

• Extensive experience with Python.

• Proficient in Machine Learning models and familiar with Data Science libraries such as Scikit-learn, XGBoost, and LightGBM.

• Practical experience with Large Language Models (LLMs) and Generative AI solutions, focusing on agent-based architectures, including RAG (Retrieval-Augmented Generation).

• Familiarity with Databricks.

• Experience with the LangChain and LangGraph frameworks.

• Knowledge of experimentation tools (MLflow).

• Familiarity with AWS Bedrock.

• Understanding of language model evaluation metrics such as BLEU and ROUGE is advantageous.

• In addition to AWS expertise, knowledge of Azure is essential.