Ashiki M.

High-quality software and AI models require rigorous, multi-dimensional validation. As a Computer Science and Engineering graduate with a strong background in language and technology, I bridge the gap between traditional Software Quality Assurance (SQA) and modern AI/LLM Evaluation. I help development teams and AI companies ensure their systems are bug-free, accurate, safe, and highly performant. My unique blend of technical engineering logic and linguistic precision allows me to write robust test cases for applications while effectively benchmarking AI models for hallucinations, alignment, and edge cases. *Core Capabilities Software Quality Assurance (SQA) • Test Planning & Execution: Designing comprehensive test cases, checklists, and bug reports for web and mobile applications. • Functional & Regression Testing: Ensuring system stability across updates and verifying that user workflows match specifications. • UI/UX & Usability Testing: Auditing interfaces for user experience consistency, responsiveness, and technical performance. *AI Data Engineering & LLM Evaluation • RLHF & Prompt Validation: Testing system prompts, few-shot variations, and evaluating model outputs for factual accuracy. • Side-by-Side (SxS) Grading: Scoring and ranking competitive LLM responses using strict, multi-dimensional rubrics. • Adversarial Testing (Red Teaming): Intentionally stress-testing models to uncover vulnerabilities, bias, safety risks, and hallucinations. *Technical Toolkit • Languages & Core Tech: HTML, CSS, JavaScript, Basic Automation Concepts, Git/GitHub CAT Tools. • QA Methodologies: Manual Testing, Agile/Scrum Frameworks, Defect Lifecycle Management. • AI Evaluation Frameworks: Human-in-the-loop (HITL) pipelines, Data Annotation, RLHF alignment. If you are looking for a precision-driven engineer to safeguard your application's quality or fine-tune your generative AI models, click the 'Invite to Job' button to discuss your project requirements.