LLM-Powered Lead Generation Assistant

• Built an LLM lead generation assistant for marketing professionals.
• Performed workflow audits and optimized costs by designing a more efficient architecture.
• Automated end-to-end AI pipelines.
• Adapted and prompted LLMs for efficient data processing and content generation.
• Researched methodologies for optimizing AI infrastructure.
• Collaborated closely with Business Development professionals to achieve team goals.

CRR reflects the effectiveness of campaigns with the predictive model, and helps increase the client's profit; Optimizing the CPA for the order; Increasing the LTV of attracted users. This can be achieved by increasing the frequency of orders per user or increasing the value of the average bill Tools: Accumulating 30,000 installs, among them — at least 40% with conversion; Making recommendations for the client on unmarked events on the event map; Collecting additional raw data on the Push API and getting a key for sending s2s events; Creating a tree of user behavior; Training the model and splitting users into clusters by LTV; Starting to send a Smart Event. In July created test campaign optimized for a predictive event; Updating the settings and enriching the Smart Event with additional information Results: Optimized campaigns using Smart Event. The CRR for them became lower than the CRR of conventional campaigns; By 25% reduced CRR for the period from October 2021 to February 2022 compared to conventional campaigns; By 23% lowered CPO; 4 times increased budget of predictive ad campaigns from October to February and reduced the share of regular promotion

In the dynamic realm of banking, ensuring effective anomaly detection is paramount. Utilising my expertise in state-of-the-art ML algorithms and advanced Deep Learning techniques, I tackled this imperative at Deutsche Bank, a globally recognized leader in financial services. The solution involved several critical stages:

• Identifying relevant data from various sources.
• Researching and testing optimal Machine Learning algorithms for tabular data analysis.
• Exploring and validating appropriate Deep Learning models for extracting insights from textual data (Natural Language Processing).
• Integrating the resulting models into the rigorous banking environment, complete with all necessary software engineering components: Python, Object-Oriented Programming, Algorithm Design and Complexity, Deployment, and more.

• Hosted NLP workshops for clients, including interactive labs and demos.
• Architected an NLP pipeline to extract audio and text signals for ML algorithms.
• Provided technical analysis and consultancy for NLP projects.
• Delivered presentations on NLP advancements and applications.

• Developed UI for a CRM system with integrated Stripe-based payment modules.
• Built a responsive, cross-platform interface.
• Integrated ContentStack CMS and ApolloGraphQL APIs for dynamic content and data fetching.
• Contributed to user account functionality and payment cabinet development in a 21-person team.