Bryce Tichit

At Albert School, I engineered cutting-edge AI solutions to optimize student success. As a freelance AI Engineer, I: - Designed and implemented an advanced Generative AI-powered agentic system that could detect students' subject interests, autonomously select promising topics, and deep dive into relevant concepts - Developed a sophisticated agent architecture that generated personalized learning paths along with custom educational content and assessment quizzes to validate student understanding - Architected a robust agentic backend leveraging LangChain, LangGraph, and BAML, with data persistence handled through Supabase integration - Built an intuitive user interface using Streamlit that provided students with seamless access to their personalized learning experiences - Developed RESTful API endpoints using FastAPI to enable communication between the agentic backend and frontend components - Collaborated with educational experts to refine the system's ability to align AI-generated content with pedagogical best practices - Managed the whole infrastructure on a dedicated server using docker-compose Tech stack: Python, FastAPI, Node.js, Prisma, Supabase, LangGraph, LangChain, Streamlit, OpenAI

At OpenClassrooms, I leaded data science initiatives to enhance the student conversion lifecycle. As a freelance Data Scientist, I: - Conducted in-depth analysis of the student conversion funnel, identifying key optimization opportunities and implementing data-driven solutions - Developed a sophisticated survival analysis model to predict long-term conversion patterns, accounting for the extended decision-making journey of prospective students - Collaborated with cross-functional teams to integrate analytical insights into strategic decision-making processes - Delivered actionable recommendations to Head of Data and CTO that improved student engagement metrics and optimized marketing resource allocation - Baked my work into an Airflow Data Engineering pipeline to compute predictions on a daily basis Tech stack: Python, Jupyter, sk-learn, Airflow, Snowflake

At Inato, I led a strategic data science initiative to optimize marketing efficiency and enhance lead conversion rates. As a freelance Data Scientist, I: - Conducted comprehensive analysis of the marketing team's lead database, implementing advanced data cleaning and segmentation methodologies - Developed and deployed a lead prioritization model that successfully identified the top 10% of high-value prospects - Collaborated closely with marketing stakeholders to implement data-driven targeting strategies - Delivered actionable insights that significantly improved marketing efficiency and increased quality lead conversion rates Tech stack: Python, Plotnine, Jupyter, DBT

At Alma, I led the Data Engineering team to build and maintain a modern data infrastructure. The goal was to help business owners make data-driven decisions by improving data quality and providing efficient tools. I developed custom data connectors and designed layered BI transformations to facilitate data usage. Additionally, I helped recruiting new team members through a rigorous selection process and helped upskilling current team members thus strengthening the group's skills and expertise. I managed the Data Engineering team, coordinating efforts to build a modern data infrastructure, including an ELT datalake and data warehouse. My role included overseeing projects, managing resources, and communicating with stakeholders to ensure the success of the overall mission. As the primary support for the Data Science team, I assisted in deploying their models and resolving technical issues encountered. As the primary support for the Data Analytics team, I assisted in building analytics models, crafting advanced analytics and ensuring maintenance of the data infrastructure. The mission's outcomes include a notable improvement in data quality and the provision of effective tools for business owners.

At OpenClassroom, I mentored 5 students in Data Analysis and Data Science programs, sharing my knowledge gained from my hands-on experiences, and honed my teaching skills to give them the keys to succeed in their future professional lives. My mission involved weekly work with the students to ensure they fully understood their courses and applied their skills correctly within the context of their projects. This first contact with the world of education taught me a lot and gave me great motivation to continue in this field in the long term.

As a Data Scientist at ManoMano, I was part of the Growth & Data team, our mission was to drive growth through smart optimizations and data-driven methods. During my assignment, I mainly accomplished the following, I developed an algorithm to identify Google keywords to target, optimizing budgets and landing pages. I also improved the Google Shopping algorithm by evaluating 2M+ products daily to adjust the maximum budget according to the devices used, thus boosting growth and customer acquisition. The impact on ManoMano's growth was considerable. I developed predictive time series models using LightGBM, validated and adjusted these models to ensure their accuracy and relevance. Then, I integrated the predictive models into marketing processes to improve overall performance. I also rewrote the entire feature calculation algorithm, allowing for scalability and calculating over 500 features on a volume of 1 billion rows. I measured the actual effectiveness of the models using AB tests, and collaborated with business teams to ensure project success. I also participated in Data Science competitions to refine and improve my skills. In addition, I maintained the Data Science team's infrastructure, helped push the team's models into production, and provided ongoing support to business teams on their challenges, through analysis or simply feedback I had to give them. I conducted an in-depth analysis of delivery time estimates at ManoMano, discovering that they were too pessimistic compared to actual delivery times. By recommending the use of tracking data for delivery time calculations, I contributed to a 3% increase in the overall conversion rate.