Skip to main content
Candace HunzwiCH
Looking for a job

Candace Hunzwi

@candacehunzwi

Generative UI Research & Development Engineer at KAIST Interaction Lab, building reusable context-aware components for Maru.

Rwanda
Message

At KAIST Interaction Lab, I designed reusable components for Maru, an LLM-driven generative UI system. They help preserve and retrieve users’ information architecture, layout, and interaction preferences across conversations.

At Big Data for Smart Society: GATE Institute, I’m investigating reasoning and planning failures in LLM agents, including how those failures affect long-horizon task completion. I’m also developing a taxonomy of agent planning approaches and failure modes.

At SignVrse, I designed experiments on hierarchical representations in a MoMask RVQ-VAE for sign-language motion generation. My analysis found that the first residual codebook recovered approximately 71% of the reconstruction gap, and the first two recovered 91–92% of full six-codebook quality.

I built UbuntuTech, a Shona writing assistant combining linguistic rules with an LLM correction layer, and developed a segmentation pipeline for Ghanaian Sign Language videos that outperformed seven baselines by up to 33% in Adjusted Rand Index. My work also includes scalable market-data pipelines at Princeton University and automated testing at Econet Wireless Zimbabwe.

Experience

Work history, roles, and key accomplishments

KK
Current

Generative UI Research & Development Engineer

KAIST Interaction Lab (KIXLAB)

Aug 2026 - Present (3 months)

Designed reusable system components for Maru, an LLM-driven generative UI system, enabling persistence and context-aware retrieval. Implemented semantic relevance scoring, abstention logic, and rule lifecycle management to improve retrieval reliability.

LLM Systems
Generative UI
Contextual Relevance Scoring
Abstention
Rule Lifecycle Management
Time Weighted Decay
Retrieval Systems
Multi Turn Evaluation
Regression TestingSystem Architecture
BI
Current

AI & Machine Learning Research Engineer

Big Data for Smart Society: GATE Institute

Apr 2026 - Present (7 months)

Investigating reasoning and planning failures in large language model agents, focusing on long-horizon decision-making and task decomposition. Developing a structured taxonomy of LLM-agent planning approaches and failure modes.

Large Language ModelsAgentic AI
Planning Strategies
Task Breakdown
Replanning
Execution Reliability
Taxonomy Development
Empirical Research
IH

Generation Connect Fellow

International Telecommunication Union (ITU) & Huawei

Jun 2025 - Aug 2026 (1 year 2 months)

Selected as 1 of 31 global fellows from approximately 6,800 applicants across 156 countries. Led implementation of a community-driven digital inclusion initiative while completing mentorship and leadership training.

SI

Research & Machine Learning Engineer

SignVrse

Nov 2025 - Apr 2026 (5 months)

Designed progressive-decoding experiments to analyze hierarchical representations in a six-codebook MoMask RVQ-VAE for sign-language motion generation. Quantified codebook sensitivity and decomposed reconstruction across motion components.

Machine Learning
RVQ VAE
MoMask
Sign Language Motion Generation
Progressive Decoding
Codebook Sensitivity
Reproducible Research
Python
IM

ICT Innovations Mentor

IOM – UN Migration

Nov 2025 - Feb 2026 (3 months)

Mentored student teams developing research-driven digital solutions addressing access barriers and equity challenges in African carbon markets. Provided technical feedback on system architecture and data flows.

EZ

Quality Assurance Engineer

Econet Wireless Zimbabwe

Apr 2023 - Aug 2023 (4 months)

Automated functional and regression testing for enterprise applications using Selenium and Python, expanding automated test coverage by 25%. Optimized test execution and CI/CD validation workflows, reducing runtime by 20.2%.

Education

Degrees, certifications, and relevant coursework

Carnegie Mellon University logoCU

Carnegie Mellon University

Master of Science, Engineering Artificial Intelligence

2025 -

Activities and societies: Mastercard Foundation Scholar

Pursuing a Master of Science in Engineering Artificial Intelligence as a Mastercard Foundation Scholar, with expected completion in May 2027.

Ashesi University logoAU

Ashesi University

Bachelor of Science, Computer Science

2022 - 2025

Activities and societies: Mastercard Foundation Scholar

Earned a Bachelor of Science in Computer Science as a Mastercard Foundation Scholar, graduating in June 2025.

Availability

Looking for a job

Location

Rwanda

Authorized to work in

Salary expectations

71k+ USD

Job categories

AI ML Research Engineer
Machine Learning Engineer
Research Software Engineer
Generative UI Engineer

Interested in hiring Candace?

You can contact Candace and 600K+ other talented remote workers on Himalayas.

Message Candace

People also viewed

View all talent

Get matched with your dream remote job

Sign up now and join over 1,000,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!

Sign up
Himalayas profile for an example user named Frankie Sullivan