Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am an experienced AI Engineer specializing in designing and deploying RAG-based multi-agent systems and scalable generative AI solutions. My work involves leveraging large language models and building advanced data extraction pipelines to improve system responsiveness and performance. I am passionate about innovating in AI technology and creating efficient automated workflows. Throughout my career, I have optimized high-throughput ETL pipelines and scaled RESTful microservices for cloud environments, enhancing data ingestion and aggregation processes to support large-scale operations. I continuously enhance my technical skill set and contribute to open-source projects, focusing on AI and software engineering domains.…I am an experienced AI Engineer specializing in designing and deploying RAG-based multi-agent systems and scalable generative AI solutions. My work involves leveraging large language models and building advanced data extraction pipelines to improve system responsiveness and performance. I am passionate about innovating in AI technology and creating efficient automated workflows. Throughout my career, I have optimized high-throughput ETL pipelines and scaled RESTful microservices for cloud environments, enhancing data ingestion and aggregation processes to support large-scale operations. I continuously enhance my technical skill set and contribute to open-source projects, focusing on AI and software engineering domains.

Lorenzo Favaro

AI Engineer, Developer, Full Stack Developer, +1





I am an experienced AI Engineer specializing in designing and deploying RAG-based multi-agent systems and scalable generative AI solutions. My work involves leveraging large language models and building advanced data extraction pipelines to improve system responsiveness and performance. I am passionate about innovating in AI technology and creating efficient automated workflows. Throughout my career, I have optimized high-throughput ETL pipelines and scaled RESTful microservices for cloud environments, enhancing data ingestion and aggregation processes to support large-scale operations. I continuously enhance my technical skill set and contribute to open-source projects, focusing on AI and software engineering domains.…I am an experienced AI Engineer specializing in designing and deploying RAG-based multi-agent systems and scalable generative AI solutions. My work involves leveraging large language models and building advanced data extraction pipelines to improve system responsiveness and performance. I am passionate about innovating in AI technology and creating efficient automated workflows. Throughout my career, I have optimized high-throughput ETL pipelines and scaled RESTful microservices for cloud environments, enhancing data ingestion and aggregation processes to support large-scale operations. I continuously enhance my technical skill set and contribute to open-source projects, focusing on AI and software engineering domains.

Available to hire

I am an experienced AI Engineer specializing in designing and deploying RAG-based multi-agent systems and scalable generative AI solutions. My work involves leveraging large language models and building advanced data extraction pipelines to improve system responsiveness and performance. I am passionate about innovating in AI technology and creating efficient automated workflows.

Throughout my career, I have optimized high-throughput ETL pipelines and scaled RESTful microservices for cloud environments, enhancing data ingestion and aggregation processes to support large-scale operations. I continuously enhance my technical skill set and contribute to open-source projects, focusing on AI and software engineering domains.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Work Experience

AI Engineer III at Reply

April 1, 2025 - Present

Designed and deployed a RAG-based multi-agent system for EV charging stations that reduced issue-resolution time by 30% through automated diagnosis of hardware malfunctions and guided troubleshooting workflows, serving over 2k end users. Delivered scalable, privacy-compliant Generative AI solutions by deploying LLM-based applications on on-premise infrastructure, integrating open-source inference, GraphRAG pipelines, and advanced data extraction from property and knowledge graphs. Implemented tool orchestration using the MCP protocol with dedicated servers for modular and extensible tool management.

AI Engineer II at Reply

March 31, 2024 - August 9, 2025

Automated 90% of a bank’s email routing by implementing an end-to-end solution on Azure leveraging OCR and custom vision models to analyze content and attachments using serverless architecture, drastically improving response time. Drove measurable improvements in Generative AI system performance by engineering RAG pipeline components including chunking techniques, retrieval strategies, embedding models, inference models, and evaluation with LLM-as-a-judge, boosting accuracy and system responsiveness. Built a two-module Generative AI platform for contract generation and consultation with Langchain, FastAPI, Qdrant, and Lang Graph agents enabling SQL and RAG-based querying, delivered MVP, and designed migration plan to Azure AI Search for production deployment.

Software Engineer at Stratos

August 31, 2022 - August 9, 2025

Optimized a high-throughput, multi-process Python ETL pipeline for PepsiCo, reducing extraction time by 80% by parallelizing OLAP data processing with IPC/threading, enabling scalable SaaS delivery to Azure for 500M+ records. Built and scaled RESTful microservices (FastAPI, Docker, Kubernetes, IBM Cloud) to orchestrate internal data ingestion and aggregation pipelines, supporting increasing daily loads and improving service latency.

Software Engineer, Contract at Wedo

January 31, 2021 - August 9, 2025

Redesigned UI and backend logic of a Java-based mobile app from scratch for athlete tracking in mountain marathons, improving usability and reducing average user response time by 5% based on customer feedback. Architected and deployed Spring-based REST microservices in Docker containers to support core business infrastructure.