Mohamed H.

Key Skills

Software

Mercor

Snorkel AI

Top Subject Matter

LLM benchmarking

AI evaluation and red-teaming

LLM benchmarking dataset authoring and evaluation

Top Data Types

Text

Top Task Types

Computer Programming/Coding

Freelancer Overview

Mercor Intelligence - AI Engineer / Data Scientist / Technical Contributor/ Reviewer. Brings 19+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Mercor and Snorkel AI. Education includes Master of Data Science, University of Malaya (2019) and Bachelor of Computer Science, 6th October University (2009). AI-training focus includes data types such as Computer Code and Programming and labeling workflows including Evaluation and Rating.

Labeling Experience

Snorkel AI - AI Engineer / Task Author

Snorkel AI

Designed and implemented multi-step coding and reasoning tasks for the Terminal-Bench benchmark under the Terminus framework. Curated datasets and built automated evaluation pipelines to test complex problem-solving and reasoning capabilities in frontier GPT-level systems. Focused on dataset preparation and benchmark task authoring to enable consistent model scoring and comparison.• Authored multi-step coding/reasoning tasks for CLI/agentic evaluation.• Built automated evaluation pipelines for benchmark runs.• Curated high-difficulty datasets for LLM benchmarking.• Supported assessment of complex reasoning behaviors.

2025 - Present

Mercor Intelligence - AI Engineer / Data Scientist / Technical Contributor/ Reviewer

Mercor

Worked as an AI Engineer / Data Scientist contributing to AI evaluation workflows for LLM benchmarking and red-teaming tasks. Built and refined Python-based evaluation pipelines, grading rubrics, and reasoning frameworks to assess model performance using structured scoring. Focused on data analytics and API-driven automation to support evaluation experiments for AI labs.• Contributed to SWE-Bench related evaluation activities.• Developed/maintained evaluation pipelines and assessment rubrics.• Supported LLM red-teaming and code-review automation.• Tracked model performance metrics for ongoing benchmarking.

2024 - Present

Education

Work History