John

Key Skills

Software

Don't disclose

Other

Top Subject Matter

Backend validation quality assurance and AI-adjacent evaluation of outputs

LLM evaluation and prompt testing

Reproducible evaluation/debugging workflow for backend validation outputs

Top Data Types

Text

Top Task Types

Prompt + Response Writing (SFT)

Freelancer Overview

Software Engineer — Systems & Backend Validation (output validation, test pipeline triage, evaluation of correctness). Brings 6+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Don't disclose and Other. Education includes Bachelor of Science, University of Ibadan (2025) and Bachelor of Science, IU International University of Applied Sciences (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

Project — AI / LLM Output Evaluation Workflow

OtherPrompt + Response Writing (SFT)

Designed an LLM output evaluation workflow to score model responses against expected results using defined pass/fail criteria and rubrics. Automated prompt batching and systematic response logging to compare outputs across varied input conditions and prompt phrasings. Generated structured evaluation reports documenting failure modes and quality scores to enable iterative prompt refinement. • Defined edge case input sets and pass/fail criteria for evaluation • Implemented automated prompt batching and response logging with Python • Produced evaluation reports with model behavior patterns and quality scoring • Supported iterative refinement by analyzing recurring failure modes

2020 - Present

Software Engineer — Systems & Backend Validation (output validation, test pipeline triage, evaluation of correctness)

Don't disclose

Contributed to AI/LLM evaluation-adjacent quality workflows by designing and executing output validation logic for backend validation pipelines and structured test scenarios. Reproduced defects in isolated environments, analyzed stack traces and logs, and verified correctness against expected behaviors using automated validation scripts. Produced structured JSON-style findings and incident documentation that supported repeatable assessment of system outputs. • Wrote and executed Python validation scripts aligned with Pytest-style assertions and evaluation workflows • Reproduced failing scenarios in Docker-based environments to isolate environment vs. application defects • Performed scripted diff workflows for migration consistency checks between pre/post state snapshots • Documented root-cause and edge cases to support consistent quality assessment across sessions

2018 - 2023

Project — Python Test Pipeline Debugger

Don't disclose

Built a test pipeline debugger that replayed failing backend validation scenarios and serialized annotated findings into structured reports. Captured stack traces, identified root causes, and mirrored Pytest-style fixture setup and assertion debugging patterns. Enabled reproducible validation runs by integrating the debugger into a Git branching workflow with tagged releases. • Replayed failing validation scenarios and generated stack-trace-based findings • Serialized root-cause annotations into structured JSON reports • Integrated debugger with Git branching and tagged validation runs • Automated environment-specific reproductions to standardize repeat testing

2021 - 2022

Education

Work History