Santi Cuni

Building a new automated system that collects the most relevant financial information in the market (especially news and audio recordings) and, through some process, provides the financial analyst with the most pertinent information to support their daily work. Extract and rate the overall sentiment expressed in the financial data. Classify the primary market sector (Energy / Technology / Finance / Others), and its related sub-sectors highlighted in the financial data. Evaluate the impact on the financial market and assign it a priority level (High, Medium, or Low). Generate for each financial data, a Title that reflects the main topic described, and a summary to give a concise and precise description of the content. Generate a Report with the processed financial news item structured as follows: ########################################################################### o Financial News Intelligence System o Date: <> o Title: <> o Summary: <> o Sentiment: <> o Sector: <> ###########################################################################

Responding correctly, in time, and with a follow-up to the service complaints has been the request that the municipality has made of me. For this reason, I have deployed an LLM-powered service assistant, enhanced with prompt engineering techniques to automate the following tasks: Complaint categorization: Correctly classify the complaint into one Category and assign it to the concerned department Complaint prioritization: Assign urgency (High/Medium/Low) based on safety and criticality of the complaints Acknowledgment drafting: Generate polite, formal, consistent acknowledgments to reassure customers, following the below structure: ########################################################################### Dear <Citizen Name>, We have received your complaint regarding <Category> at this location. Our records indicate that this issue involves <Issue> and has been ongoing for <Duration or Time>. The Priority assigned to your complaint is < Priority>. We are committed to fixing this issue quickly and will provide updates. Thank you for bringing this to our attention. Regards, Municipal Support Team ###########################################################################

Developing predictive models to estimate: House prices are predicted using features such as pollution levels, number of rooms, and proximity to employment centers, thereby improving pricing accuracy. Built pricing models to predict used car values based on factors like mileage, brand, model, and year, supporting revenue optimization, developing profitable business strategies, and increasing market share. The LOS (Length of Stay) utilizes available data (collected during admission and after running a few tests), including Department, Age, and Admission Deposit, to improve resource allocation (such as beds and ventilators). Developed models to identify high-conversion contacts among leads, optimizing resource allocation and marketing efforts. Analyzed factors driving contact conversion and created profiles for likely conversions, enhancing lead targeting. Developed credit scoring models aligned with EU Consumer Credit Directive (CCD) guidelines, streamlining decision-making for home equity lines of credit. Identified key features influencing the target to inform strategic business decisions. Sometimes, deploy a Docker container for a batch inference application. Presented findings and final reports to management, enabling informed decision-making

Translating business requirements into technical specifications, estimating solution costs, and performing gap analysis to ensure project alignment Leading the Telephony Operations department for daily operations and team management, optimizing service delivery Collaborating with engineering teams to plan and execute migration from Cisco Voice, Video, and Collaboration platforms to M365, ensuring seamless transition. Training Service Desk staff and end users on troubleshooting and utilizing collaboration tools, increasing user adoption.

Delivering Unified Collaboration services to clients across financial, IT, education, aerospace, and service industries in EMEA, including Credit Agricole, Cisco Systems Inc., and Airbus. Designing, Field Engineering, Layer 3 Support, and Subject Matter Expert; led projects, managed resources, and supported budget planning. Managing and developing teams of 3 to 10 members, providing training and leadership to achieve company goals.