Abdussalam A.

Key Skills

Software

Other

Top Subject Matter

STEM (Water Resources & Environmental Engineering, hydrology, hydraulics, engineering, quantitative analysis)

Academic Writing (STEM)

Prompt Engineering

Top Data Types

Text

Document

Top Task Types

RLHF

Prompt + Response Writing (SFT)

Freelancer Overview

Independent AI Model Auditor & Cross-Model Evaluator. Brings 3+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Other. Education includes Bachelor of Engineering, Ahmadu Bello University (2022). AI-training focus includes data types such as Text and labeling workflows including RLHF, Prompt + Response Writing (SFT), and Evaluation.

Labeling Experience

STEM AI Domain Expert — Final Year Research Project

OtherText

Produced expert-verified, fact-checked technical documents used for STEM AI training data. Applied systematic fact-checking, source validation, and evidence-based quality control to research outputs for model training. Generated and annotated responses in hydrology, hydraulics, and environmental science for training and evaluation tasks. • Synthesized literature and primary data for factuality benchmarking • Validated every quantitative claim and methodological step in the content • Delivered gold-standard, structured STEM text for AI learning • Performed annotation and expert-level QA of STEM academic content

2024 - Present

Independent AI Model Auditor & Cross-Model Evaluator

OtherTextRLHF

Developed and refined an analytical evaluation framework to assess multiple AI models on reasoning and factual consistency. Conducted structured comparisons of model outputs across complex prompts, scoring for accuracy and logical soundness. Identified, documented, and iterated on model failure patterns including hallucination and overconfidence for prompt engineering refinement. • Applied qualitative and quantitative scoring rubrics for response calibration • Engineered prompts for adversarial probing and nuanced model testing • Used AI platforms such as Claude, ChatGPT, Grok, and Gemini in daily model evaluation tasks • Provided expert judgment and feedback in an RLHF and side-by-side comparison setting

2024 - Present

Developer — AI-Powered Academic Writing Toolkit

OtherTextPrompt + Response Writing (SFT)

Built and deployed an AI writing toolkit, engaging in prompt engineering for reliable and precise academic content creation. Iteratively evaluated and annotated output quality, identifying errors and refining responses within a RLHF framework. Authored gold-standard examples for model learning as part of comprehensive unique content creation tasks. • Defined system prompts and user instructions for consistency and factual precision • Applied output evaluation, re-prompting, and annotative feedback • Focused on STEM academic text generation and quality assurance • Modeled ideal response patterns to guide AI performance

2024 - 2024

Education

Work History