Tejas K.

Key Skills

Software

Data Annotation Tech

Top Subject Matter

LLM factual accuracy

Safety Domain Expertise

and logical reasoning (coding/math/problem solving)

Top Data Types

Text

Top Task Types

Entity (NER) Classification

Freelancer Overview

Freelance AI Evaluator - Outlier.AI. Brings 2+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Data Annotation Tech. Education includes Bachelor of Engineering, SNJB College Of Engineering (SPPU) (2022) and Higher Secondary Certificate, Late B.G Kabra College Of Science (2022). AI-training focus includes data types such as Text and labeling workflows including Evaluation, Rating, and Named Entity Recognition.

Labeling Experience

Freelance AI Evaluator - Outlier.AI

Entity (NER) Classification

Worked as a freelance AI evaluator to create domain-specific prompts for assessing the quality of frontier large language models. Focused on testing models for factual accuracy, safety, and logical reasoning under varied coding, math, and problem-solving scenarios. Required strong prompt engineering skills and a solid understanding of evaluation for reliability and model behavior in real-world tasks. • Engineered coding, math, and reasoning prompts for stress-testing LLMs • Evaluated responses for factual accuracy, safety, and logical coherence • Assessed model behavior across domain-specific and adversarial scenarios • Iterated prompt designs to improve evaluation coverage

2025 - 2026

Freelance AI Trainer (Outlier.ai | DataAnnotation.tech) — 2025 to 2026

Data Annotation TechText

Performed AI training and evaluation work by engineering domain-specific prompts to assess frontier LLMs. Focused on stress-testing model outputs for factual accuracy, safety, and logical reasoning. Used prompt-based test cases to guide model behavior and judge response quality. • Built complex coding/math/problem-solving prompts • Evaluated outputs for factual correctness • Assessed safety and logical reasoning • Conducted iterative prompt refinement for robustness

2025 - 2026

Education

Work History