Stella

Key Skills

Software

No software listed

Top Subject Matter

Accident severity prediction for emergency triage (hospital and law enforcement contexts)

ML model training for critical accident detection and severity prediction

Legal Services & Contract Review

Top Data Types

Text

Document

Top Task Types

Data Collection

Fine-tuning

Freelancer Overview

AI/ML Engineer | Product Manager at Crash.ai (AI/ML-powered MVP development). Brings 8+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Internal and Proprietary Tooling. Education includes Master of Science, Northeastern University (2026) and Bachelor of Arts, University of Wisconsin-Madison. AI-training focus includes data types such as Medical, DICOM, and Computer Code and labeling workflows including Data Collection and Fine-tuning.

Labeling Experience

AI/ML Engineer | Product Manager at Crash.ai (training pipeline optimization and model tuning)

Fine-tuning

Optimized machine learning training pipelines on a large accident-related dataset to reduce model training time and improve overall model effectiveness. Conducted evaluation and tuning across multiple ML/AI models to achieve performance gains suitable for production use. Used iterative experimentation practices to accelerate training and refine model behavior. • Trained and tuned 8+ ML/AI models • Reduced training time by 60% through pipeline evaluation and tuning • Improved critical accident detection from 10% to 87% • Worked with a 7.7M-record dataset to drive model improvements

2015 - 2015

AI/ML Engineer | Product Manager at Crash.ai (AI/ML-powered MVP development)

Data Collection

Built an AI/ML MVP to support hospital accident triage by translating domain pain points into machine-learning product requirements. Participated in preparing and structuring training data to enable accident severity prediction. Focused on improving model performance for real-world emergency workflows. • Defined product requirements from hospital and law enforcement workflows • Supported the preparation of training inputs for accident severity prediction • Worked on evaluation-oriented improvements to increase detection accuracy • Enabled deployment readiness by aligning model objectives with operational needs

2015 - 2015

Education

Work History