Data Scientist at OMTPME (2024-02 – Present)
Develop, train, evaluate, and iterate on machine learning and deep learning models covering the full life cycle from feature engineering to production-ready deployment.
- Develop, train, evaluate, and iterate on machine learning and deep learning models (classification, regression, clustering) covering the full life cycle from feature engineering to production-ready deployment.
- Designed and maintain end-to-end Data pipelines for the collection, cleaning, integration and automated enrichment of large-scale structured and unstructured datasets from heterogeneous sources.
- Perform exploratory data analysis (EDA), detect trends and anomalies, and produce economic indicators, sectoral reports, and impactful visualizations for decision-makers.
- Apply statistical and econometric methods (OLS, Logit, hypothesis testing) to analyze causal relationships, measure impacts, and support evidence-based decision-making.
- Translate complex business requirements into scalable data & AI solutions, and communicate findings to both technical and non-technical audiences through clear reporting and storytelling.
- Apply structured problem-solving to ambiguous data and business challenges, breaking them down into clear analytical steps and delivering reliable, explainable solutions.
- Conduct regular technological watch on advancements in AI, machine learning, NLP, and LLMs to continuously improve methods, adopt emerging tools, and propose innovative solutions.
Data Scientist at CMAIS (2023-02 – 2023-08)
Developed and implemented NLP models and pipelines for text understanding and analysis.
- Developed and implemented NLP models and pipelines, including named entity recognition, abstractive text summarization, document classification (ML & DL), and sentiment analysis.
- Automated data collection workflows through web scraping and built end-to-end processing pipelines integrating multiple AI techniques for text understanding and analysis.
