Edson – Python, LLM, RAG

Software engineering and technology consulting company delivering custom digital products, cloud solutions, data platforms, and AI-powered systems for enterprise clients across multiple industries.

• Led and mentored LLM Engineers across multiple projects, providing guidance on architecture, code reviews, and engineering best practices;
• Participated in technical reviews and strategic discussions with the client, contributing to solution design and technical direction;
• Conducted technical interviews at Taller for Data Science and AI roles, evaluating candidates on statistical modeling, machine learning, and problem-solving skills.

Software engineering and technology consulting company delivering custom digital products, cloud solutions, data platforms, and AI-powered systems for enterprise clients across multiple industries.

• Designed and developed intelligent chatbot solutions, including real-time applications using WebSockets and REST APIs;
• Built and maintained Retrieval-Augmented Generation (RAG) pipelines using LangChain, LangGraph, and LangSmith;
• Integrated proprietary LLMs, including OpenAI models via Azure OpenAI and Anthropic models via AWS Bedrock, as well as open-source models from Hugging Face;
• Developed advanced text-to-SQL, Q&A, conversational, and multi-agent applications powered by LLMs;
• Designed and reviewed architectures for AI-driven solutions, focusing on scalability, reliability, and maintainability;
• Applied software engineering best practices, including design patterns and clean code principles, to build robust and reusable components;
• Implemented LLM guardrails to mitigate prompt injection, PII leakage, and harmful content generation in AI assistants;
• Monitored AI applications and conducted experiments, evaluations, and validations using LangSmith.

Cloud-native enterprise integration platform (iPaaS) enabling organizations to connect applications, data, APIs, and legacy systems through scalable integration and automation workflows, with AI-powered applications developed to enhance customer experience.

• Developed AI-powered applications to improve customer experience;
• Improved platform task efficiency and reduced onboarding time for new customers;
• Built chatbots and AI-powered applications integrated into the platform;
• Created AI solutions using LangChain, LlamaIndex, CrewAI, vector databases, and Neo4j;
• Designed and implemented AI agents;
• Applied prompt engineering, RAG, GraphRAG, and fine-tuning techniques;
• Integrated OpenAI, Google, and open-source models into AI solutions;
• Built APIs using FastAPI and Pydantic, applying established design patterns;
• Collaborated with cross-functional and international teams.

Built ML classification models to predict components at risk of failure, improving maintenance planning by helping crews prioritize high-risk locations. Developed and trained the models using Amazon SageMaker Notebooks and Studio.

• Developed and evaluated ML classification models;
• Collaborated with business stakeholders to clarify requirements and align modeling approaches with business needs;
• Developed unit tests and maintained the codebase in line with software engineering standards.

Built an AIOps system to automatically classify and route support tickets to the appropriate teams, replacing a slow manual process. The solution evolved from classical NLP and ML approaches using BERT, FastText, and Random Forest on Databricks to prompt engineering with Llama 2.

• Developed an LLM-based solution for automated support ticket classification and routing;
• Owned development of the end-to-end codebase supporting the classification solution;
• Deployed and served the model in production using model serving infrastructure.

Digital document and electronic signature platform enabling businesses to automate secure, legally valid contract and signing workflows.

• Performed customer segmentation and clustering to identify behavioral patterns and support business analysis;
• Built time-series models to forecast revenue and profitability for upcoming months;
• Developed classification models to predict customer conversion likelihood;
• Conducted data analysis and generated insights to support marketing initiatives and decision-making;
• Developed data science solutions using Python, NumPy, Pandas, SQL, and AWS SageMaker;
• Worked with AWS infrastructure and data services, including Lambda, Redshift, S3, EC2, and ECS.

Digital document and electronic signature platform enabling businesses to automate secure, legally valid contract and signing workflows.

• Applied Python engineering best practices, including PEP 8 and test-driven development (TDD);
• Developed and maintained API integrations with internal and external services;
• Containerized applications and services using Docker;
• Managed infrastructure as code using Terraform;
• Worked with AWS and PostgreSQL to support cloud-based applications and data workflows;
• Built ETL pipelines and automated workflows using Apache Airflow and Python.