Data Scientist & ML Engineer
Abhi Erra
I build modeling systems that improve real-world infrastructure.
I design and build data-driven systems and machine learning solutions that address complex, real-world challenges. I specialize in modeling infrastructure that is not only effective but also reliable, interpretable, and built for production.
Featured Projects
Systems and analyses built for clarity and deployment.
ABRA
A full-stack ML solution for automating the analysis of Auditory Brainstem Responses (ABRs) in mice, including data preprocessing, convolutional neural network-based peak detection, threshold analysis, and a Streamlit UI for batch uploads and visualization.
ETA Accuracy & Route Quality Analysis
An end-to-end analytics platform to evaluate and improve ETA predictions using NYC taxi trip data. Includes model development in PyTorch, PostgreSQL integration, advanced segmentation metrics, and detailed failure-mode analyses.
Philosophy on Data and Modeling
I believe strong modeling is defined by clarity of assumptions, rigorous evaluation, and systems that fail gracefully when confronted with real-world complexity. I’m drawn to challenging domains like healthcare, transportation, and public infrastructure, where ambiguity, messy data, and high stakes demand thoughtful design.
Rather than favoring complexity for its own sake, I prioritize:
- Interpretable models that stakeholders can understand
- Robust evaluation frameworks tied to real performance
- Sustainable systems that integrate with product and infrastructure stacks
The goal is not just to fit data — but to build tools and systems that teams can trust and iterate on in production.
Contact me
Open to collaboration, consulting, and roles where ML meets real-world impact.