Everlyne K.

Key Skills

Software

Don't disclose

AWS SageMaker

Appen

Clickworker

CloudFactory

Google Cloud Vertex AI

Top Subject Matter

Multilingual learning with NLP and LLM fine-tuning

Document OCR and LLM-powered report generation

Legal Services & Contract Review

Top Data Types

Text

Document

Image

Top Task Types

Fine-tuning

Question Answering

Segmentation

RLHF

Freelancer Overview

Software Engineer | Nyansapo AI (AI training / LLM fine-tuning for Swahili assessments). Brings 8+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Don't disclose. Education includes Bachelor of Science, The Catholic University of Eastern Africa. AI-training focus includes data types such as Text and Document and labeling workflows including Fine-tuning and Question Answering.

Labeling Experience

Senior Software Engineer | AInspect (LLM automation and structured extraction for inspection reports)

Don't discloseDocumentQuestion Answering

Added LLM features to automate report generation within an inspection platform workflow. Enhanced the report engine using OCR to convert document text into structured data for downstream processing and output. Supported LLM-driven automation to produce and generate PDFs from extracted and structured inspection information. • Integrated LLM features for automated report creation • Used OCR and structured extraction for report data • Implemented PDF generation from structured outputs • Designed inspection microservices for scalable AI automation

2025 - Present

Software Engineer | Nyansapo AI (AI training / LLM fine-tuning for Swahili assessments)

Don't discloseTextFine-tuning

Worked on an AI-powered multilingual learning platform that incorporated NLP modules for comprehension scoring and feedback. Led fine-tuning of custom LLMs to generate Swahili assessment outputs for learners, improving accessibility for local audiences. Applied retrieval-augmented generation (RAG) to produce context-aware responses during instruction and assessment flows. • Trained/fine-tuned LLMs for Swahili assessments • Built comprehension scoring and feedback using NLP • Implemented RAG for accurate context-aware answers • Refactored AI-serving APIs to improve stability and response times

2024 - 2025

Education

Work History