Haris B.

Key Skills

Software

Don't disclose

Other

Scale AI

Top Subject Matter

Enterprise LLM evaluation and AI model training (RLHF/alignment-style work)

AI-assisted coding

prompt-based response generation

Top Data Types

Text

Top Task Types

Prompt + Response Writing (SFT)

Entity (NER) Classification

Freelancer Overview

LLM/AI Trainer at Turing (Remote). Brings 4+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Don't disclose, Other, and Scale AI. Education includes Bachelor of Science, University of Education (2025). AI-training focus includes data types such as Computer Code and Programming and labeling workflows including Evaluation, Rating, and Prompt + Response Writing (SFT).

Labeling Experience

LLM/AI Trainer at Turing (Remote)

Don't disclose

Trained and evaluated LLM outputs to ensure alignment with task objectives, safety standards, and business requirements. Tested Tencent AI models for adherence to constraints by probing edge cases and validating policy-compliant behavior. Reviewed and graded AI agent responses on specialized workflows to provide detailed performance analysis and improve reliability. • Evaluated and refined enterprise-scale AI model behavior through large-scale testing. • Assessed constraint-following and detection of improper bypass attempts. • Performed systematic review and scoring of AI responses for real-world task execution. • Contributed to benchmarking and readiness improvements for deployment.

2025 - 2026

Competitive Coder - Scale AI

Scale AIEntity (NER) Classification

Worked as a competitive coder by solving large volumes of programming challenges to strengthen algorithmic problem-solving. Wrote efficient and optimized C++ solutions designed to pass extensive test suites. Also experimented with AI-assisted coding workflows by generating and refining solutions using prompts and reviewing model outputs.• Solved 100+ coding challenges and improved competitive programming skills.• Developed optimized C++ programs for problems with 1000+ test cases.• Used prompt-based approaches to generate code responses and evaluated results.• Edited and debugged code produced by multiple AI tools to fix errors and ensure accuracy.

2023 - 2024

Competitive Coder / AI-assisted coding work at Scale AI

OtherPrompt + Response Writing (SFT)

Generated AI responses by crafting appropriate prompts and evaluating the results to support coding challenge solutions. Wrote and debugged code produced by multiple AI tools to improve functionality and fix errors. Conducted quality checks for correctness and reliability, including identifying code likely generated by AI systems. • Prompted ChatGPT for coding solutions and assessed response quality. • Edited and debugged AI-generated code from 10+ AI tools. • Detected AI-generated code and verified accuracy across 1000+ test cases. • Delivered consistent performance on 100+ programming challenges to strengthen tooling outputs.

2023 - 2024

Education

Work History