Natia K.

Key Skills

Software

Don't disclose

Other

Top Subject Matter

Medical/ophthalmology (clinical decision support, medical reasoning)

Ophthalmology/clinical medicine (LLM-powered decision support)

Applied AI (chatbots and agents

Top Data Types

Text

Image

Top Task Types

Function Calling

Fine-tuning

Freelancer Overview

AI Evaluation & Medical Domain Expert (LLM response evaluation and clinical accuracy assessment). Brings 18+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Don't disclose, Internal, and Proprietary Tooling. Education includes Doctor of Medicine, Tbilisi State Medical University (2009) and Residency, Ogarev Mordovia State University (2016). AI-training focus includes data types such as Text, Medical, and DICOM and labeling workflows including Evaluation, Rating, and Function Calling.

Labeling Experience

AI Evaluation & Medical Domain Expert (LLM response evaluation and clinical accuracy assessment)

Don't discloseText

Conducted evaluation of LLM-generated clinical responses for factual accuracy and clinical soundness. Assessed clinical reasoning quality, factual correctness, and logical consistency to refine output reliability for medical use. Supported development of an LLM-powered clinical decision-support workflow using prompt design and response testing. • Evaluated medical accuracy of model responses • Rated/assessed clinical reasoning and factual correctness • Ensured logical consistency across outputs • Performed iterative refinement based on evaluation results

2025 - Present

Applied AI training (Artificial Intelligence Practical Course; AI Chatbot & Agents Course)

OtherTextFine-tuning

Completed applied AI training focused on building and understanding AI chatbots and agentic systems. Strengthened skills relevant to training and evaluation workflows for LLM-based applications. Used coursework outcomes to support medical AI development activities. • Applied AI training via structured courses • Learned chatbot and agent concepts applicable to LLM systems • Strengthened knowledge for building/evaluating AI workflows • Used training to support clinical AI tooling efforts

2025 - 2026

Clinical decision-support application builder using Anthropic Claude API (prompting + evaluation)

Function Calling

Developed and validated an LLM-powered clinical decision-support system with an emphasis on medically accurate outputs. Used structured prompt design and testing to ensure responses align with clinical requirements and reference expectations. Integrated model response evaluation into the application workflow for medical accuracy monitoring. • Prompt design and testing for clinical decision support • Evaluation of model responses for medical accuracy • Creation of reference answers for medical reasoning • Integration of LLM outputs into a clinical tool

2025 - 2026

Education

Work History