Data Scientist resume template (LaTeX)

\documentclass[a4paper,10pt]{article}

\usepackage[a4paper, top=0.5in, bottom=0.5in, left=0.6in, right=0.6in]{geometry}
\usepackage{titlesec}
\usepackage{enumitem}
\usepackage[hidelinks]{hyperref}

\pagestyle{empty}
\raggedright
\setlength{\tabcolsep}{0in}
\setlist[itemize]{noitemsep, topsep=1pt, leftmargin=*}

\titleformat{\section}{\vspace{4pt}\scshape\raggedright\large}{}{0em}{}[\titlerule]

\newcommand{\entry}[4]{
  \item
    \begin{tabular*}{\textwidth}{l@{\extracolsep{\fill}}r}
      \textbf{#1} & #2 \\
      \textit{#3} & \textit{\small #4} \\
    \end{tabular*}
}

\begin{document}

\begin{center}
  {\LARGE \textbf{Aisha Karim}} \\[3pt]
  Senior Data Scientist $|$ London, UK $|$ +44 7700 900 412 \\
  \href{mailto:aisha.karim@example.com}{aisha.karim@example.com} $|$
  \href{https://github.com/aishakarim}{github.com/aishakarim} $|$
  \href{https://linkedin.com/in/aishakarim}{linkedin.com/in/aishakarim}
\end{center}

\section{Summary}
Data scientist with 6 years of experience taking models from notebook to production in
fintech and e-commerce. Strongest in causal inference, forecasting and experimentation
platforms; comfortable owning the full lifecycle from problem framing to monitoring.

\section{Experience}
\begin{itemize}[leftmargin=*, label={}]
  \entry{Monzo Bank}{London, UK}{Senior Data Scientist, Financial Crime}{Mar 2023 -- Present}
  \begin{itemize}
    \item Built a gradient-boosted fraud model (LightGBM) scoring \textbf{2M} payments/day; cut fraud losses \textbf{23\%} at a fixed false-positive rate.
    \item Designed a real-time feature store on BigQuery + Dataflow, reducing feature latency from minutes to \textbf{under 300ms}.
    \item Introduced SHAP-based reason codes that shortened analyst review time by \textbf{35\%} and satisfied FCA explainability requirements.
  \end{itemize}
  \entry{ASOS}{London, UK}{Data Scientist, Pricing \& Forecasting}{Sep 2020 -- Feb 2023}
  \begin{itemize}
    \item Replaced a rules-based markdown engine with a hierarchical demand forecast, adding \textbf{GBP 4.1M} gross margin in year one.
    \item Ran \textbf{40+} A/B tests on the experimentation platform; wrote the team's guide to CUPED and sequential testing.
  \end{itemize}
  \entry{Deloitte}{Manchester, UK}{Analyst, Data \& Analytics}{Aug 2019 -- Aug 2020}
  \begin{itemize}
    \item Delivered churn and customer-lifetime-value models for two FTSE 100 retail clients.
  \end{itemize}
\end{itemize}

\section{Selected Projects}
\begin{itemize}
  \item \textbf{causal-uplift} (open source, 900+ GitHub stars): Python library for uplift modelling with meta-learners and Qini evaluation.
  \item \textbf{Kaggle M5 Forecasting}: top 2\% (silver medal) with a LightGBM ensemble over 30,490 hierarchical time series.
\end{itemize}

\section{Publications}
\begin{enumerate}
  \item Karim, A., Patel, R. (2024). Delayed-label learning for payment fraud. \textit{KDD Workshop on Anomaly Detection in Finance}.
  \item Karim, A. (2022). Hierarchical reconciliation for fashion demand. \textit{International Symposium on Forecasting}.
\end{enumerate}

\section{Education}
\begin{itemize}[leftmargin=*, label={}]
  \entry{University College London}{London, UK}{M.Sc. Data Science and Machine Learning, Distinction}{2018 -- 2019}
  \entry{University of Manchester}{Manchester, UK}{B.Sc. Mathematics, First Class Honours}{2015 -- 2018}
\end{itemize}

\section{Skills}
\textbf{Modelling}: gradient boosting, causal inference, time-series forecasting, Bayesian methods, NLP \\
\textbf{Engineering}: Python, SQL, PySpark, dbt, Airflow, Docker, MLflow, FastAPI \\
\textbf{Cloud \& Data}: GCP (BigQuery, Vertex AI, Dataflow), AWS (SageMaker, S3), Snowflake

\end{document}