condensed insight

Author: boada

boada-cv.tex

@@ -65,6 +65,7 @@ \section{Professional \newline Experience}
 
 \textit{Senior Machine Learning Engineer} \hfill \textbf{January, 2021 - 2024}\newline
     \begin{list2}
+        	\vspace*{-5mm}
         \item Designed, built, and maintained ML infrastructure and tools, including autoML, CI/CD (Jenkins, GitHub Actions), model tracking (MLflow), and orchestration (Airflow) to support data-driven decision-making.
         \item Crafted and implemented policy for external data ingestion and retention to ensure accessibility and proper data stewardship across the organization.
         \item Developed near-realtime applications (via Spark streaming) to identify and mitigate in-game cheating and malicious behaviors, achieving action times in the low 10s of seconds.
@@ -79,9 +80,8 @@ \section{Professional \newline Experience}
 \textit{Fellow} \hfill \textbf{January, 2020 - 2021}\newline
     \begin{list2}
     	\vspace*{-5mm}
-      \item Helped optimize the way NYC health inspectors perform restaurant inspections in order to reduce the time critical health violations remain unaddressed.
-    	\item Trained a random forest in Python to prioritize NYC restaurant inspections based on environmental variables and their past inspection histories and provided the results to NYC through an API deployed on AWS.
-    	\item Resulted in NYC inspectors identifying $\sim$2.5\% more violations in the first half of an inspection window,  leading to critical violations being discovered up to 7 days earlier than by the current approach implemented by NYC.
+        \item Completed a data science bootcamp focused on transitioning academics into the tech industry, working on real-world data problems.
+        \item Built a random forest model in Python to prioritize NYC restaurant inspections, improving violation detection by 2.5\% and identifying critical issues up to 7 days earlier through an AWS-deployed API.
     \end{list2}
 \vspace*{-2mm}