Nicholas R.

Key Skills

Software

Other

Top Subject Matter

Audio signal processing and anomaly detection for industrial equipment

Content moderation systems

Research data processing and dataset annotation

Top Data Types

Audio

Text

Top Task Types

Classification

Data Collection

Freelancer Overview

Audio Analysis Pipeline (feature extraction for anomaly detection). Brings 9+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal, Proprietary Tooling, and Other. Education includes Bachelor of Science, University of Maryland, College Park (2018) and AWS Certified Cloud Practitioner, Amazon Web Services. AI-training focus includes data types such as Audio, Text, and Computer Code and labeling workflows including Classification and Data Collection.

Labeling Experience

Research Data Processing (automated cleaning and annotation)

Data Collection

Automated cleaning and annotation of large research datasets to improve data quality and reduce manual effort. The labeling effort focused on preparing datasets for later modeling and analysis workflows by standardizing and enriching existing records. This enabled more consistent annotations at scale for a research lab setting.• Performed automated data cleaning to increase dataset reliability.• Supported dataset annotation to prepare structured training or analysis inputs.• Reduced manual annotation effort by 60% while improving overall data quality.

2018

Content Moderation Dashboard (human-in-the-loop review workflow)

OtherTextClassification

Built a content moderation dashboard enabling human moderators to review flagged audio and text items. The system supported labeling/review workflows by presenting flagged content for assessment and routing decisions. This reduced moderator turnaround time by streamlining the review experience and improving operational throughput.• Supported moderator review of flagged audio and text content in a dedicated UI.• Helped operationalize classification decisions within a moderation workflow.• Improved response time by 40% through faster review and handling.

2018

Audio Analysis Pipeline (feature extraction for anomaly detection)

AudioClassification

Developed an audio anomaly detection pipeline by extracting MFCC features from industrial equipment audio streams to identify early failure patterns. The work involved transforming raw audio into machine-learning-ready features and enabling automated detection based on those features. This contributed to supervised model workflows where audio segments are categorized as anomalous or normal.• Extracted MFCCs and spectrogram-style features from audio streams for downstream detection.• Implemented preprocessing to prepare audio-derived features for machine learning.• Enabled evaluation of anomaly detection accuracy for early failure identification.

2018

Education

Work History