Amber B.

Key Skills

Software

AWS SageMaker

Anno-Mage

Appen

Argilla

Axiom AI

Clickworker

CloudFactory

CrowdFlower

CrowdSource

CVAT

Data Annotation Tech

Dataloop

Datatroniq

Datumbox

Datasaur

Datature

Dataturk

Deep Systems

Diffgram

Doccano

Encord

Figure Eight

Google Cloud Vertex AI

Hasty

HiveMind

Humanatic

Img Lab

iMerit

Kili Technology

Labelbox

LabelImg

Label Studio

LightTag

Lionbridge

Mercor

Micro1

Mighty AI

Mindrift

OneForma

OpenCV AI Kit (OAK)

Playment

Prodigy

Redbrick AI

Remotasks

Roboflow

Sama

Scale AI

Sloth

Snorkel AI

SuperAnnotate

Supervisely

Tagtog

Surge AI

Toloka

Telus

Trilldata Technologies

VoTT

V7 Labs

Other

Internal/Proprietary Tooling

Top Subject Matter

LLM-powered document information extraction

Classification Domain Expertise

and summarization

Top Data Types

Document

Text

Computer Code Programming

Top Task Types

Function Calling

Classification

Question Answering

Point/Key Point

Object Detection

Text Generation

Text Summarization

Red Teaming

Computer Programming/Coding

Data Collection

Evaluation/Rating

Transcription

Freelancer Overview

Senior Full Stack & AI Engineer, NBCUniversal — LLM agent workflows for document processing. Brings 13+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes Master of Science, University of North Carolina at Charlotte (2015) and Bachelor of Engineering, VNR VignanaJyothi Institute of Engineering & Technology (JNTU-Hyderabad) (2013). AI-training focus includes data types such as Document and Text and labeling workflows including Function Calling, Classification, and Question Answering.

Labeling Experience

Senior Full Stack & AI Engineer, NBCUniversal — LLM agent workflows for document processing

OtherDocumentFunction Calling

Built multi-agent workflows that automatically extract, classify, and summarize information from PDFs, emails, SharePoint, and web sources. Used LangChain Agents with custom tool definitions and function-calling APIs to perform LLM-driven processing of unstructured content. The outputs support downstream retrieval and knowledge tasks for enterprise users. • Extracted structured information from heterogeneous document sources. • Performed classification of content segments for organization and routing. • Generated concise summaries for faster human review. • Integrated function-calling style behaviors via agent orchestration.

2023 - Present

AI/ML project referenced in resume — RAG Document Q&A System

OtherDocumentQuestion Answering

Developed RAG-style question answering capability by building an enterprise document ingestion and retrieval pipeline for precise answers. The approach ingests PDFs and SharePoint documents, chunks and embeds content, and serves responses with citations. This enables automated knowledge retrieval from document collections. • Ingested and processed unstructured enterprise documents (PDFs, SharePoint). • Chunked and embedded document content for retrieval. • Used a conversational Q&A interface to answer questions. • Returned source citations to support answer verification.

2013 - Present

Senior Software Engineer — Full Stack, HCLTech — Support ticket classifier model training and deployment

OtherTextClassification

Trained and deployed an AI model to automatically categorize incoming customer support tickets. The system used historical JIRA ticket text features to learn a multi-class classifier for automated routing and triage. The trained model was packaged as a Python microservice integrated via a REST API. • Engineered TF-IDF features from ticket text for multi-class classification. • Trained a scikit-learn classifier to achieve high categorization accuracy. • Deployed the classifier as a microservice for operational use. • Integrated predictions into the ticketing workflow via REST APIs.

2019 - 2023

Education

Work History