Shad Javed Ansari

Key Skills

Software

CVAT

LabelImg

Label Studio

Roboflow

Other

Top Subject Matter

AI Response Evaluation

Prompt Engineering

Model QA

Top Data Types

Computer Code Programming

Image

Text

Video

Document

Top Task Types

Classification

Computer Programming/Coding

Evaluation/Rating

Prompt + Response Writing (SFT)

Segmentation

Freelancer Overview

LLM Evaluation Engineer (SxS Evaluation & Model QA). Brings 3+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Internal and Proprietary Tooling. AI-training focus includes data types such as Text, Computer Code, and Programming and labeling workflows including Evaluation and Rating.

Labeling Experience

AI Data Processing & Automation Tasks (Python-Based)

OtherComputer Code ProgrammingClassificationEvaluation Rating

Worked on Python-based AI training tasks involving automation-style workflows, structured data processing, and AI output evaluation. My responsibilities included writing and debugging Python scripts, extracting and transforming structured data (CSV, JSON, Markdown), and validating outputs against strict formatting and project guidelines. I reviewed and corrected AI-generated code and technical responses, fixed logical and syntax errors, and ensured consistency and correctness across datasets. The project required strong attention to detail, adherence to instructions, and self-QA to deliver reliable, machine-ready outputs for AI training.

Worked on Python-based AI training tasks involving automation-style workflows, structured data processing, and AI output evaluation. My responsibilities included writing and debugging Python scripts, extracting and transforming structured data (CSV, JSON, Markdown), and validating outputs against strict formatting and project guidelines. I reviewed and corrected AI-generated code and technical responses, fixed logical and syntax errors, and ensured consistency and correctness across datasets. The project required strong attention to detail, adherence to instructions, and self-QA to deliver reliable, machine-ready outputs for AI training.

2024 - 2025

LLM Coding Evaluator & QA Analyst (Freelance / Contract)

In this ongoing role, I evaluate large language model-generated programming solutions for correctness, efficiency, and robustness. I design adversarial tests, verify outputs through execution, and provide structured feedback on algorithmic reasoning and solution clarity. My evaluations are aimed at improving model reliability and identifying common failure patterns. • Assessed computer code for correctness and edge-case handling • Detected hallucinated APIs and logical inconsistencies • Provided feedback and suggested optimizations to improve models • Designed and administered adversarial tests for model evaluation

In this ongoing role, I evaluate large language model-generated programming solutions for correctness, efficiency, and robustness. I design adversarial tests, verify outputs through execution, and provide structured feedback on algorithmic reasoning and solution clarity. My evaluations are aimed at improving model reliability and identifying common failure patterns. • Assessed computer code for correctness and edge-case handling • Detected hallucinated APIs and logical inconsistencies • Provided feedback and suggested optimizations to improve models • Designed and administered adversarial tests for model evaluation

2024 - Present

LLM Evaluation Engineer (SxS Evaluation & Model QA)

Text

As an LLM Evaluation Engineer, I conducted rigorous side-by-side evaluations of AI-generated responses using structured rubrics. I focused on assessing factual accuracy, logical consistency, and relevance to real-world scenarios. My duties included detecting hallucinations, ranking outputs, and designing challenging prompts to test model weaknesses. • Evaluated AI responses by factual and logical criteria • Identified hallucinations and fabricated information in outputs • Designed realistic and adversarial prompts for robustness testing • Provided justifications and corrections based on rubric scoring

As an LLM Evaluation Engineer, I conducted rigorous side-by-side evaluations of AI-generated responses using structured rubrics. I focused on assessing factual accuracy, logical consistency, and relevance to real-world scenarios. My duties included detecting hallucinations, ranking outputs, and designing challenging prompts to test model weaknesses. • Evaluated AI responses by factual and logical criteria • Identified hallucinations and fabricated information in outputs • Designed realistic and adversarial prompts for robustness testing • Provided justifications and corrections based on rubric scoring

2026 - 2026

Python Face Recognition Attendance System (AI-Assisted Automation Project)

OtherImageClassificationObject Detection

Developed a Python-based face recognition system to automate attendance tracking using computer vision techniques. The project involved implementing automation workflows for image capture, face detection, recognition, and structured attendance logging. I processed and stored outputs in structured formats (CSV/JSON), debugged Python scripts to improve accuracy and reliability, and validated results across different scenarios and edge cases. The project demonstrates hands-on experience with Python automation, AI-assisted workflows, and image-based data processing.

Developed a Python-based face recognition system to automate attendance tracking using computer vision techniques. The project involved implementing automation workflows for image capture, face detection, recognition, and structured attendance logging. I processed and stored outputs in structured formats (CSV/JSON), debugged Python scripts to improve accuracy and reliability, and validated results across different scenarios and edge cases. The project demonstrates hands-on experience with Python automation, AI-assisted workflows, and image-based data processing.

2024 - 2024

Image Annotation & AI Training Support Tasks

RoboflowImageSegmentationClassification

Supported computer vision AI training projects involving image annotation and dataset validation. Responsibilities included classifying and segmenting visual elements, reviewing annotations for accuracy, and ensuring consistency with project-specific guidelines. Performed quality checks, corrected annotation errors, and maintained clean, structured datasets suitable for machine learning model training and evaluation.

Supported computer vision AI training projects involving image annotation and dataset validation. Responsibilities included classifying and segmenting visual elements, reviewing annotations for accuracy, and ensuring consistency with project-specific guidelines. Performed quality checks, corrected annotation errors, and maintained clean, structured datasets suitable for machine learning model training and evaluation.

2023 - 2024

Education

Work History