For employers

Hire this AI Trainer

Sign in or create an account to invite AI Trainers to your job.

LoginCreate account
Invite to Job
A
Apurv Singh

Apurv Singh

AI Product Evaluation Specialist

India flagGurgaon, India
$30.00/hrIntermediateOtherRemotasksScale AI

Key Skills

Software

Other
RemotasksRemotasks
Scale AIScale AI

Top Subject Matter

LLM Outputs
AI Product Evaluation
Email Spam Detection

Top Data Types

TextText
ImageImage
Computer Code ProgrammingComputer Code Programming

Top Task Types

ClassificationClassification

Freelancer Overview

AI Product Evaluation Specialist. Brings 1.5+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include internal, proprietary tooling, and Other. Education includes Bachelor of Technology, Galgotias University (2024). AI-training focus includes data types such as Text and labeling workflows including Evaluation, Rating, and Classification.

IntermediateEnglishHindi

Labeling Experience

AI Product Evaluation Specialist

Text
As an AI Product Evaluation Specialist, I designed and executed structured evaluation frameworks to assess LLM-generated model outputs. I evaluated AI responses based on reasoning quality, instruction adherence, and hallucination risk, handling over 100 model responses per week. I also implemented feedback loops to improve model performance through RLHF cycles and prompt optimization. • Developed structured evaluation rubrics for LLM output quality. • Conducted quality audits and compliance validation against specifications. • Identified recurring failure patterns to inform optimization strategies. • Enhanced RLHF training cycles with actionable feedback for production models.

As an AI Product Evaluation Specialist, I designed and executed structured evaluation frameworks to assess LLM-generated model outputs. I evaluated AI responses based on reasoning quality, instruction adherence, and hallucination risk, handling over 100 model responses per week. I also implemented feedback loops to improve model performance through RLHF cycles and prompt optimization. • Developed structured evaluation rubrics for LLM output quality. • Conducted quality audits and compliance validation against specifications. • Identified recurring failure patterns to inform optimization strategies. • Enhanced RLHF training cycles with actionable feedback for production models.

2025 - Present

Project: LLM Evaluation & Output Optimization

OtherText
I developed scoring rubrics and evaluation criteria to measure reasoning quality, hallucination risk, and instruction adherence of LLM outputs. This involved benchmarking outputs across different model versions and providing detailed, structured feedback. The evaluation directly informed model fine-tuning and iteration. • Built prompt evaluation rubrics for systematic LLM output review. • Benchmarked outputs from multiple model versions. • Assessed instruction adherence and hallucination frequency. • Delivered structured recommendations for output optimization.

I developed scoring rubrics and evaluation criteria to measure reasoning quality, hallucination risk, and instruction adherence of LLM outputs. This involved benchmarking outputs across different model versions and providing detailed, structured feedback. The evaluation directly informed model fine-tuning and iteration. • Built prompt evaluation rubrics for systematic LLM output review. • Benchmarked outputs from multiple model versions. • Assessed instruction adherence and hallucination frequency. • Delivered structured recommendations for output optimization.

2024 - 2024

Machine Learning Project: Email Spam Classifier

OtherTextClassification
For a machine learning project, I built a classifier to detect spam and malicious content in email inboxes using labeled datasets. I performed precision and recall optimization to limit false positives and improve classification accuracy. The project required hands-on data annotation and model evaluation. • Used Python and labeled datasets to classify spam emails. • Manually reviewed and adjusted labels for training accuracy. • Evaluated model performance through iterative testing cycles. • Focused on improving false-positive rates and classifier reliability.

For a machine learning project, I built a classifier to detect spam and malicious content in email inboxes using labeled datasets. I performed precision and recall optimization to limit false positives and improve classification accuracy. The project required hands-on data annotation and model evaluation. • Used Python and labeled datasets to classify spam emails. • Manually reviewed and adjusted labels for training accuracy. • Evaluated model performance through iterative testing cycles. • Focused on improving false-positive rates and classifier reliability.

2023 - 2023

Education

G

Galgotias University

Bachelor of Technology, Computer Science

Bachelor of Technology
2024 - 2024

Work History

A

Axponent

Product Analyst

Gurgaon
2024 - 2025
T

The Good Glamm Group

Marketing Intern

Chattarpur
2023 - 2023