Todd P.

Key Skills

Software

No software listed

Top Subject Matter

Legal deposition analysis

witness behavior credibility scoring

fraud detection

Top Data Types

Text

Document

Top Task Types

Text Generation

Data Collection

Freelancer Overview

Lead Software Engineer — AI-powered analysis platforms (LLMs, NLP, CV, fraud modeling). Brings 13+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Hugging Face, OpenCV, and PyTorch. Education includes Bachelor’s Degree, North Carolina State University (2014). AI-training focus includes data types such as Computer Code and Programming and labeling workflows including Text Generation, Data Collection, and Computer Programming.

Labeling Experience

Lead Software Engineer — AI-powered analysis platforms (LLMs, NLP, CV, fraud modeling)

Text Generation

Built and deployed multiple AI features including LLM-based deposition analysis and NLP pipelines for credibility scoring. Developed predictive and event-driven workflows that transform model outputs into analytics and decision support for production systems. • Used LLMs and Hugging Face to extract insights from deposition text • Implemented real-time witness behavior analysis with OpenCV, PyTorch, and NLP sentiment plus micro-expression detection • Built AI-based fraud detection using LSTMs, TensorFlow, and Kafka for predictive modeling and throughput • Deployed and operationalized AI services within cloud and API architectures to support downstream applications.

2023 - Present

Full Stack Engineer — Data/telemetry pipeline work supporting AI training and evaluation

Data Collection

Contributed to AI/ML-related system capabilities by integrating telemetry, analytics, and event-driven data pipelines that support model development and evaluation. Implemented scalable ingestion and monitoring mechanisms across cloud environments to ensure reliable data flow for downstream AI features. • Implemented analytics and telemetry pipelines using Google Analytics and internal tracking systems • Integrated event-driven asynchronous processing using Pub/Sub and Kafka • Improved reliability and observability via health checks, circuit breakers, retries, and structured logging • Automated CI/CD for auditable releases to support data-driven product iterations.

2019 - 2023

Software Engineer — ML model integration into UI workflows

Performed software engineering work that specifically supported machine learning integration into application user workflows. Focused on integrating Python-driven model components with staged document and clinical trial platform capabilities. • Ensured seamless ML model integration into UI workflows using Python • Built a staging area subsystem for regulated clinical trial documents • Designed and implemented REST APIs using Spring MVC with a thin-controller architecture • Integrated staging workflows with an existing versioning pipeline to maintain audit traceability.

2017 - 2019

Full Stack Developer — Event-driven systems for data ingestion supporting AI/ML pipelines

Data Collection

Supported AI system integration and structured data handling by building secure enterprise platforms that used event-driven architectures and cloud messaging for downstream AI workflows. Implemented API gateway security, infrastructure automation, and observability to enable consistent data acquisition and processing. • Developed real-time internal systems using WebSockets and event-driven architecture with Pub/Sub and Firestore triggers • Designed and deployed a secure OAuth2-based API gateway with Spring Security and rate limiting • Standardized monitoring/observability using Prometheus, Grafana, and Stackdriver • Migrated services into containerized microservices to improve operational reliability for analytics/ML pipelines.

2014 - 2017

Education

Work History