Alex K.

Key Skills

Software

Other

Top Subject Matter

LLM evaluation and AI content quality assurance

Synthetic speech evaluation

Prompt engineering and LLM response improvement

Top Data Types

Text

Audio

Image

Top Task Types

Prompt + Response Writing (SFT)

RLHF

Freelancer Overview

Independent AI Evaluator (Portfolio) – Text response evaluation. Brings 1+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes Bachelor of Science, Moi University (2027). AI-training focus includes data types such as Text and Audio and labeling workflows including Evaluation, Rating, and Prompt + Response Writing (SFT).

Labeling Experience

Independent AI Evaluator (Portfolio) – Preference ranking for RLHF-style alignment

OtherTextRLHF

Performed human-feedback style evaluations to support RLHF-like quality alignment by scoring and ranking model outputs. Compared answers to determine which responses better meet correctness, helpfulness, and instruction-following requirements. Produced consistent feedback that can be used as supervision signals for training and fine-tuning processes. • Output comparison for preference signals • Scoring/rating for alignment criteria • Feedback intended for training supervision • Instruction-following and quality-focused ranking

2026 - Present

Independent AI Evaluator (Portfolio) – Prompt engineering for improved outputs

OtherTextPrompt + Response Writing (SFT)

Applied prompt engineering techniques to refine inputs and improve downstream AI response quality during evaluation activities. Wrote and iterated prompts based on observed failure modes such as poor reasoning, incorrect facts, and weak instruction following. Used these iterations to inform better response generation behavior in LLM development workflows. • Prompt iteration to address quality gaps • Incorporating evaluation findings into prompt edits • Improving response quality through prompt engineering • Supporting LLM behavior refinement via human feedback

2026 - Present

Independent AI Evaluator (Portfolio) – Synthetic speech evaluation

OtherAudio

Evaluated synthetic speech samples by reviewing audio quality and overall speech characteristics. Provided structured, human feedback intended to improve the quality of speech generation. Ensured evaluations aligned with established criteria for speech performance and user-facing clarity. • Synthetic speech quality assessment • Structured feedback provision • Criteria-based evaluation of speech outputs • Human rating to guide improvements

2026 - Present

Independent AI Evaluator (Portfolio) – Text response evaluation

OtherText

Independently evaluated AI-generated text responses for correctness, factuality, reasoning quality, and instruction following using structured evaluation guidelines. Performed comparative assessments across model outputs and generated preference rankings to support LLM alignment and quality improvement. Assessed fluency, coherence, and contextual accuracy to provide consistent human feedback. • Correctness and factuality checks • Reasoning and instruction-following evaluation • Preference ranking between outputs • Language quality and contextual accuracy review

2026 - Present

Independent AI Evaluator - Independent AI Evaluator

Audio

Provided independent evaluation of AI-generated outputs to assess quality, correctness, and instruction following against structured guidelines. Conducted comparative reviews between model responses and produced preference rankings for selection decisions. Delivered clear, structured feedback to support improvements in language fluency, contextual accuracy, and synthetic speech quality. • Evaluated factuality, reasoning, and adherence to prompts • Reviewed language coherence, fluency, and contextual correctness • Assessed synthetic speech quality and generated structured notes • Applied prompt engineering insights to refine response quality

2026 - 2026

Education

Work History