cv
Basics
| Name | Dan Smith |
| Label | Data Scientist |
| dsmith.smith864@gmail.com | |
| Url | https://smith478.github.io/ |
| Summary | Data Scientist with an interest in medical applications |
Work
- 2025.10 - Now
Staff Data Science Engineer
Censys
Building host reputation scoring and automated cybersecurity fingerprint generation using LLMs.
- Built host reputation scoring system in Go that assigns reputation scores to IPs at scale
- Developed automated cybersecurity fingerprint generation pipeline using LLMs and an evolutionary approach
- 2024.06 - 2025.10
Full Stack AI Engineer
MOTOR Information Systems
Using LLMs to extract structure out of unstructured text.
- Used dynamic RAG to extract classification from unstructured text
- Helped build production application in Sagemaker and Kubeflow
- Built agentic system to standardize raw manufacturer text data
- 2019.08 - 2024.06
Lead Data Scientist
Instinct Science
Building out Analytics and Data Science applications, developing and deploying machine learning models, and setting up cloud infrastructure for reporting.
- 2017.08 - 2024.06
Senior Data Scientist - Consultant
Rocket Mortgage
Build and support computer vision, large language, and multimodal models focused on automated processing of financial and appraisal documents.
- 2014.07 - 2017.08
Actuarial Technician
Auto-Owners Insurance
Built models to predict claim severity and frequency to price commercial insurance policies.
- 2013.07 - 2014.07
Visiting Assistant Professor
Furman University
Conducted research in the area of differential geometry and taught undergraduate courses in mathematics.
Education
Projects
- 2023.12 - Now
- 2024.01 - Now
Medical Summarization and Transcription
Tools for transcribing medical audio data with summarization and question-answering.
Skills
| Deep Learning | |
| Transformers - Language and Vision | |
| Computer Vision - Classification, Localization, Object Detection | |
| TensorFlow | |
| PyTorch | |
| HuggingFace |
| Classical Machine Learning | |
| Generalized Linear Models | |
| Ensemble Models - Random Forest, Gradient Boosting | |
| Support Vector Machines | |
| Statistical Methods - ANOVA, Clustering, PCA |
| Programming | |
| Python | |
| Go | |
| SQL | |
| Git | |
| Docker | |
| AWS |
Publications
-
2015.11 The Behavior of the Chern Scalar Curvature under the Chern-Ricci Flow
Proceedings of the American Mathematical Society
We showed that finite-time singularities in the Chern-Ricci flow are characterized by the blow-up of the scalar curvature of the Chern connection.
-
2013.08 Stability of the Almost Hermitian Curvature Flow
arxiv
I showed that Kähler-Einstein structures are stable under small perturbations for a new geometric flow, Almost Hermitian Curvature Flow, for Calabi-Yau manifolds and manifolds with a negative first Chern class.
Volunteer
- 2018.02 - 2018.05
Instructor
Detroit Area Pre-College Engineering Program (DAPCEP)
Taught middle school students programing and hardware basics.
- Built raspberry pi based computers
- Taught basic programming
- 2016.10 - 2017.08
Data Analyst
Volunteers of America
Performed data analytics on the effectiveness of programs.
- Performed exploratory data analysis on medical data to support grant applications
Certificates
| Exam S (Statistics and Probabilistic Models) | ||
| Casualty Actuarial Society | 2016-05 |
| Exam C (Construction and Evaluation of Actuarial Models) | ||
| Casualty Actuarial Society | 2015-06 |
| Exam MFE (Models for Financial Economics) | ||
| Casualty Actuarial Society | 2014-11 |
| Exam FM (Financial Mathematics) | ||
| Casualty Actuarial Society | 2014-06 |
| Exam P (Probability) | ||
| Casualty Actuarial Society | 2014-03 |