Kondwani N.

Key Skills

Software

Google Cloud Vertex AI

Other

Top Subject Matter

Generative AI Q&A system

Data governance and analytics enablement for ML readiness

Top Data Types

Computer Code Programming

Top Task Types

Text Generation

Freelancer Overview

Project: Generative AI Q&A system using LLMs (Google Cloud Vertex AI). Brings 6+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Google Cloud Vertex AI and Other. Education includes Bachelor of Science, Africa University and Master's, University of North Texas. AI-training focus includes data types such as Computer Code and Programming and labeling workflows including Text Generation, Evaluation, and Rating.

Labeling Experience

Project: Generative AI Q&A system using LLMs (Google Cloud Vertex AI)

Google Cloud Vertex AIText Generation

Designed and implemented a system that uses large language models to generate accurate responses for complex questions by defining a novel data model and distributed computing approach. Worked with Google Cloud Vertex AI to enable scalable and real-time Q&A behavior for user queries. Focused on structuring and operationalizing AI workflows that depend on high-quality labeled/structured inputs and evaluation cycles. • Modeled Q&A data representations for downstream model use • Implemented distributed computing techniques for scalable inference • Leveraged LLMs via Google Cloud Vertex AI • Ensured output quality for question answering use cases

2024 - 2026

Opulence: Data Analyst/Business Analyst (data quality and modeling enablement)

Other

Contributed to deep learning and analytical model development by building reporting frameworks and automating workflows that improve data quality for analytics consumption. Applied statistical and data analysis techniques to identify trends and improvement opportunities, supporting more reliable downstream model training and evaluation. Led stakeholder workshops aimed at improving data management practices, which is essential for consistent labeling/ground-truth generation. • Improved data accuracy and accessibility for analytics • Automated recurring reporting to reduce manual effort • Designed data models for forecasting and performance tracking • Conducted stakeholder workshops to strengthen data governance

2021 - 2023

Education

Work History