Fernando Barscevicius

Fernando Barscevicius  new_releases

About

Detail

Machine Learning Engineer | Data Scientist
São Paulo, State of São Paulo, Brazil

Contact Fernando regarding: 
work
Full-time jobs
Starting at USD10k/month
Flexible work
Starting at USD70/hour

Timeline


work
Job
school
Education

Résumé


Jobs verified_user 9% verified
  • TRICURA INSURANCE GROUP
    Machine Learning & Data Science Tech Lead verified_user Verified experience
    TRICURA INSURANCE GROUP
    Jan 2026 - Current (5 months)
    Building the Data Science and ML disciplines from scratch, reporting directly to the CEO and CTO. Established the ML/Data Science function from zero: defined the technical roadmap with C-level executives, designed the MLOps platform, and built cross-functional workflows with engineering and product teams. Fine-tuned BERT models using Hugging Face and PyTorch to extract key information from nursing notes. Created patient risk prediction models (fall risk, hospitalization, mortality) using boosting models, advanced feature engineering, and Bayesian optimization. Designed and implemented batch scoring deployment with Docker and Airflow.
  • TRICURA INSURANCE GROUP
    Machine Learning Engineer
    TRICURA INSURANCE GROUP
    Jan 2025 - Current (1 year 5 months)
    Building the ML and Data Science function from scratch, reporting directly to the CEO and CTO. I design the MLOps infrastructure, fine-tune language models for healthcare document understanding, and build risk prediction systems. Working with LLMs for data labeling and model monitoring.
  • Self-Employed
    Machine Learning Consultant
    Self-Employed
    Apr 2024 - Jan 2025 (10 months)
    Full ownership of end-to-end ML projects across different industries, balancing business requirements with technical feasibility while managing client relationships directly. Built a text-to-SQL system using LLMs, AWS Bedrock, and LangGraph that let business leaders query data without SQL knowledge. Created the first credit scoring engine for a fintech startup focused on home equity loans.
  • C
    Lead Data Scientist
    C6 Bank
    Jan 2023 - Mar 2024 (1 year 3 months)
    Led a team of 7 data scientists building CRM and propensity models. Increased conversion rates for key offerings by 15% through product propensity scores. Cut propensity model development time from 12 weeks to 4 weeks by creating a Python library, templates, and checklists. Led income estimation model rebuild that corrected 40% of misclassified high-income customers and reduced operational costs by 20%. Improved team retention by 25% through regular 1:1s, brainstorming sessions, and code reviews.
  • Nubank
    Staff Data Scientist public Remote experience
    Nubank
    Aug 2021 - Sep 2022 (1 year 2 months)
    Focused on NLP systems for customer support. This role taught me to prioritize data quality over model complexity. Diagnosed a two-year cycle of declining model performance by identifying root cause in data labeling processes, leading to simpler models that outperformed complex deep learning approaches while being cheaper to run. Reduced support wait times by 20% and operational costs by 10% by improving NLP models and integrating new data sources into auto-reply and routing systems. Built a clickstream data pipeline that became a company-wide resource, with app behavior data nearly matching query text importance in routing decisions.
  • J
    Senior Data Scientist public Remote experience
    Juvo
    Sep 2020 - Aug 2021 (1 year)
    At a small startup, titles meant little. I worked across ML, product decisions, sales calls, backend engineering, and data strategy. Implemented Scrum methodology, reducing development cycles from 2 months to 2 weeks. Built off-the-shelf credit risk scores from mobile transaction data and automated backtesting, cutting SLA from 1 week to 1 day. Additionally, I leveraged Microsoft Power BI to build business-facing dashboards, providing key stakeholders with clear insights into project performance and data-driven decision-making.
  • Grupo ZAP
    Data Scientist
    Grupo ZAP
    Aug 2019 - Sep 2020 (1 year 2 months)
    Learned to collaborate with engineers and product teams to design scalable ML products. Built a search ranking system tailored to user preferences, improving CTR by 17%. Created an NLP fraud detection model and image-based duplicate listing detector, increasing revenue by 7%. Developed and maintained business-facing dashboards using Tableau to visualize key performance indicators and provide actionable insights to stakeholders, thereby supporting data-driven decision-making across departments.
  • M
    Data Scientist
    Method Data Science
    Jun 2018 - Sep 2018 (4 months)
    Joined a mentorship program to learn from experienced data scientists while doing pro-bono work for US startups. Analyzed health sensor data from sleep monitors to measure the impact of a light-based sleep intervention. Built models to predict flu outbreaks across the US using public health data.
  • M
    Machine Learning Engineer
    Marketdata
    Sep 2017 - Aug 2019 (2 years)
    My first ML role. Focused on understanding business problems and delivering targeted solutions. Automated analytical processes for statisticians, improving productivity by 30%. Deployed a recommender system for a major fashion retailer, boosting revenue by 15%.
  • M
    Data Science Intern
    Marketdata
    Sep 2017 - Dec 2018 (1 year 4 months)
    - Built the company's first deep learning solution - a Tensorflow based recommender system for Brazil's largest fashion industry, which lead to a 35% increase in recommended purchases conversion when compared to their former rule-based recommender Built the company's first deep learning solution - a Tensorflow based recommender system for Brazil's largest fashion industry, which lead to a 35% increase in recommended purchases conversion when compared to their former rule-based recommender
  • N
    Research Assistant
    National University of Ireland, Galway
    May 2016 - Jul 2016 (3 months)
  • General Motors
    CAD/CAM Programmer | Prototype Development
    General Motors
    Feb 2002 - Jul 2013 (11 years 6 months)
Education verified_user 0% verified
  • Business Science University
    Data Science
    Business Science University
    Jan 2018 - Jan 2019 (1 year 1 month)
  • freeCodeCamp
    Full Stack Web Development Certification, Computer Programming
    freeCodeCamp
    Jan 2018 - Jan 2019 (1 year 1 month)
  • Universidade Federal do ABC
    Bachelor of Science
    Universidade Federal do ABC
    Jan 2015 - Current (11 years 5 months)
  • Universidade Federal do ABC
    Bachelor of Science in Neuroscience
    Universidade Federal do ABC
    Jan 2015 - Current (11 years 5 months)
  • N
    Science without Borders, Cognitive Science
    National University of Ireland, Galway
    Jan 2015 - Jan 2016 (1 year 1 month)