Hamphry Kisanya

Key Skills

Software

Telus

Top Subject Matter

AI Agent Evaluation and Policy Logic

AI Model Scenario Testing and Evaluation

AI Customer Service Policy Evaluation

Top Data Types

Text

Computer Code Programming

Top Task Types

Question Answering

Text Summarization

Transcription

Data Collection

Computer Programming Coding

Freelancer Overview

Freelance QA Analyst for Autonomous AI Agents. Brings 6+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal, Proprietary Tooling, and Telus. Education includes Master of Science, University of Nairobi (2019) and Bachelor of Technology, University of Nairobi (2017). AI-training focus includes data types such as Text and labeling workflows including Evaluation and Rating.

Labeling Experience

Freelance QA Analyst for Autonomous AI Agents

Text

I evaluated complex task structures, policy logic, and agent actions for autonomous AI agents. My focus was on ensuring logical consistency, completeness, and realism in AI agent assessments. I proposed gold standards and collaborated with developers to refine systems for scenario-based testing. • Coordinated analysis of ambiguous AI behaviors and missing assumptions. • Suggested expected behaviors for agent actions and task refinements. • Analyzed failure modes to make AI agent testing align with real-world scenarios. • Used structured frameworks to provide critical feedback and improvement recommendations.

I evaluated complex task structures, policy logic, and agent actions for autonomous AI agents. My focus was on ensuring logical consistency, completeness, and realism in AI agent assessments. I proposed gold standards and collaborated with developers to refine systems for scenario-based testing. • Coordinated analysis of ambiguous AI behaviors and missing assumptions. • Suggested expected behaviors for agent actions and task refinements. • Analyzed failure modes to make AI agent testing align with real-world scenarios. • Used structured frameworks to provide critical feedback and improvement recommendations.

2023 - Present

Research Analyst

TelusText

I led research to improve AI model performance through scenario-based testing and evaluated machine learning logic. Responsibilities included assessing structured data using various formats and identifying inconsistencies. I contributed to the performance and effectiveness assessment of AI systems in practical projects. • Designed assessment methodologies for real-world logic validation. • Worked with datasets in JSON and YAML for accurate testing. • Led initiatives to pinpoint weaknesses and propose AI system enhancements. • Ensured AI models met structured evaluation standards.

I led research to improve AI model performance through scenario-based testing and evaluated machine learning logic. Responsibilities included assessing structured data using various formats and identifying inconsistencies. I contributed to the performance and effectiveness assessment of AI systems in practical projects. • Designed assessment methodologies for real-world logic validation. • Worked with datasets in JSON and YAML for accurate testing. • Led initiatives to pinpoint weaknesses and propose AI system enhancements. • Ensured AI models met structured evaluation standards.

2021 - 2022

Logic & Policy Evaluation Consultant

Text

I conducted policy evaluation and logic-based assessments for AI-powered customer service automation projects. My work focused on uncovering potential logical breakdowns and providing robust systemic feedback. I collaborated with teams to ensure decision processes reflected real-world service needs. • Identified edge cases indicative of model shortcomings. • Provided feedback on unrealistic scenarios or misalignments. • Supported developers in aligning AI decision systems with practical expectations. • Applied systems thinking methodology for comprehensive test coverage.

I conducted policy evaluation and logic-based assessments for AI-powered customer service automation projects. My work focused on uncovering potential logical breakdowns and providing robust systemic feedback. I collaborated with teams to ensure decision processes reflected real-world service needs. • Identified edge cases indicative of model shortcomings. • Provided feedback on unrealistic scenarios or misalignments. • Supported developers in aligning AI decision systems with practical expectations. • Applied systems thinking methodology for comprehensive test coverage.

2020 - 2021

AI Research Intern

Text

I supported the design and testing of AI evaluation tasks for educational AI systems. Key responsibilities included validating AI models' handling of logic problems and decision-making scenarios. I provided actionable feedback to refine and enhance educational AI model responses. • Analyzed AI handling of logical problem-solving in educational tasks. • Evaluated AI responses for accuracy and robustness. • Suggested model refinements based on testing results. • Fostered improvements in AI for education technology.

I supported the design and testing of AI evaluation tasks for educational AI systems. Key responsibilities included validating AI models' handling of logic problems and decision-making scenarios. I provided actionable feedback to refine and enhance educational AI model responses. • Analyzed AI handling of logical problem-solving in educational tasks. • Evaluated AI responses for accuracy and robustness. • Suggested model refinements based on testing results. • Fostered improvements in AI for education technology.

2019 - 2019

Quality Assurance Research Intern

Text

I prepared test cases and evaluated AI models for anomaly detection accuracy. My role focused on identifying critical edge cases and failure modes in machine learning systems. I summarized testing results to guide improvement initiatives for model robustness. • Developed targeted test cases for real-world anomaly detection scenarios. • Evaluated outcomes and reported critical findings for remediation. • Documented areas of improvement for ML model robustness. • Contributed to quality assurance processes in AI systems.

I prepared test cases and evaluated AI models for anomaly detection accuracy. My role focused on identifying critical edge cases and failure modes in machine learning systems. I summarized testing results to guide improvement initiatives for model robustness. • Developed targeted test cases for real-world anomaly detection scenarios. • Evaluated outcomes and reported critical findings for remediation. • Documented areas of improvement for ML model robustness. • Contributed to quality assurance processes in AI systems.

2018 - 2018

Show more

Education

Work History