Liben T.

Key Skills

Software

Label Studio

Scale AI

Labelbox

Top Subject Matter

Software Engineering / Computer Science

Cybersecurity / Information Security

Artificial Intelligence / Machine Learning

Top Data Types

Computer Code Programming

Text

Document

Top Task Types

RLHF

Red Teaming

Transcription

Evaluation/Rating

Computer Programming/Coding

Data Collection

Text Generation

Text Summarization

Freelancer Overview

Liben Tadele Full Stack Developer specializing in AI-powered applications [email protected] +251983388751 Addis Ababa, Ethiopia Male Ethiopian SUMMARY Full Stack Developer specializing in AI-powered applications, LLM integrations, and Machine Learning solutions. Experienced in building scalable web applications using modern frameworks and integrating intelligent systems such as chatbots and automation tools. Strong background in cybersecurity and penetration testing, ensuring secure and robust application development. Passionate about solving real-world problems with efficient and secure code. SKILLS Full Stack Development React.js / Next.js • Node.js / Express • HTML, CSS, JavaScript • REST APIs • AI / Machine Learning / LLM Python • TensorFlow / PyTorch • OpenAI API / LLM integration • NLP basics • Cybersecurity / Penetration Testing Web Application Penetration Testing (OWASP Top 10) • API Security Testing (REST / JSON endpoints) • Authentication & Session Management Attacks • Directory & Endpoint Discovery (Fuzzing) • Input Validation & Injection Testing (SQLi, XSS basics) • Access Control & Authorization Testing (IDOR) • Reconnaissance & Enumeration (Subdomains, Services) • Network Scanning & Service Analysis • HTTP Request Manipulation & Traffic Analysis • Vulnerability Assessment & Basic Exploitation • Linux-Based Security Testing (Kali Linux) • Tools & Systems Git / GitHub • Docker • Linux • PROJECTS School Management System 02/2026 – Present Developed a full-sta

Labeling Experience

AI Response Evaluation & Code Quality Assessment

Computer Code ProgrammingEvaluation/Rating

Evaluating and rating AI-generated responses and code outputs for quality, correctness, and safety as part of LLM training workflows. Tasks include assessing Python and JavaScript code for logical accuracy, identifying edge cases, rating responses for helpfulness and factual grounding, and flagging unsafe or incorrect outputs. Applied domain expertise in full stack development and web application security to provide high-signal feedback on technical tasks.

2026 - Present

LLM Benchmark Task Authoring & AI Output Evaluation

Computer Code ProgrammingComputer Programming/Coding

Authored and evaluated tasks for LLM training and benchmarking projects on the Revelo platform, including TerminalBench (terminal/CLI command reasoning tasks) and PR Writer (pull request description generation evaluation). Work involved writing ground-truth examples, assessing AI-generated outputs for correctness and quality, and providing structured feedback to improve model behavior on developer-facing tasks. Applied real-world software development experience to produce high-signal training data.

2025 - Present

Education

Work History